Commit
•
4c2ae1f
1
Parent(s):
8007cf3
v0 model
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +10 -0
- checkpoint-100/config.json +3 -0
- checkpoint-100/generation_config.json +3 -0
- checkpoint-100/model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +3 -0
- checkpoint-100/tokenizer.json +3 -0
- checkpoint-100/tokenizer_config.json +3 -0
- checkpoint-100/trainer_state.json +823 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/config.json +3 -0
- checkpoint-200/generation_config.json +3 -0
- checkpoint-200/model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +3 -0
- checkpoint-200/tokenizer.json +3 -0
- checkpoint-200/tokenizer_config.json +3 -0
- checkpoint-200/trainer_state.json +1613 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/config.json +3 -0
- checkpoint-300/generation_config.json +3 -0
- checkpoint-300/model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +3 -0
- checkpoint-300/tokenizer.json +3 -0
- checkpoint-300/tokenizer_config.json +3 -0
- checkpoint-300/trainer_state.json +2403 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-385/config.json +3 -0
- checkpoint-385/generation_config.json +3 -0
- checkpoint-385/model.safetensors +3 -0
- checkpoint-385/optimizer.pt +3 -0
- checkpoint-385/rng_state.pth +3 -0
- checkpoint-385/scheduler.pt +3 -0
- checkpoint-385/special_tokens_map.json +3 -0
- checkpoint-385/tokenizer.json +3 -0
- checkpoint-385/tokenizer_config.json +3 -0
- checkpoint-385/trainer_state.json +3070 -0
- checkpoint-385/training_args.bin +3 -0
- config.json +3 -0
- generation_config.json +3 -0
- model.safetensors +3 -0
- special_tokens_map.json +3 -0
- tokenizer.json +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-385 filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
config.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
checkpoint-100 filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
checkpoint-200 filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
checkpoint-300 filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
generation_config.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322b2d3fc9de58487c02f1cd651d484d73244f9704de3d5feea36d002a38af0f
|
| 3 |
+
size 748
|
checkpoint-100/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82bdd024a0ba026e4001e0433d3922a27b1242913db7be87e2851d17165b99c8
|
| 3 |
+
size 111
|
checkpoint-100/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c902b8779329b72d13123abd190eb8abc4874034542d6460c812f4c0c4ef2630
|
| 3 |
+
size 810702192
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3aeba7985871af574775ffc9bc3f54f8a5465bd3fe06cabad919da69c90c5ad
|
| 3 |
+
size 1621580026
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c26b481b9cb8c27b6ce66e286d7b2720e0aefc60735ac6e7640899dd50d4bf55
|
| 3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88d741f650ae118917922caa09145405cb8755dac6ba17ed9172d579629982fe
|
| 3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8
|
| 3 |
+
size 473
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870f4e2baa6b683221fa52004d5d6f40ab8c9d31961617304b78c910c2c3caf2
|
| 3 |
+
size 2114042
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c4f587ac3a67c3964d3e84248f95ffc8e4f0e64d9de677692df39aa35eb2d11
|
| 3 |
+
size 4845
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,823 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.25915127955944284,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0025915127955944283,
|
| 13 |
+
"grad_norm": 12.625,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.7977,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0051830255911888565,
|
| 20 |
+
"grad_norm": 12.0625,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.7787,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.007774538386783284,
|
| 27 |
+
"grad_norm": 13.0,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.8003,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.010366051182377713,
|
| 34 |
+
"grad_norm": 12.5625,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.787,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01295756397797214,
|
| 41 |
+
"grad_norm": 12.25,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.7684,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.015549076773566569,
|
| 48 |
+
"grad_norm": 12.625,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.7544,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.018140589569160998,
|
| 55 |
+
"grad_norm": 12.5,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.7769,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.020732102364755426,
|
| 62 |
+
"grad_norm": 11.4375,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.7161,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.023323615160349854,
|
| 69 |
+
"grad_norm": 11.5,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.7165,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02591512795594428,
|
| 76 |
+
"grad_norm": 12.1875,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.7437,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02591512795594428,
|
| 83 |
+
"eval_loss": 1.7256978750228882,
|
| 84 |
+
"eval_model_preparation_time": 0.0003,
|
| 85 |
+
"eval_runtime": 24.5814,
|
| 86 |
+
"eval_samples_per_second": 105.893,
|
| 87 |
+
"eval_steps_per_second": 13.262,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.02850664075153871,
|
| 92 |
+
"grad_norm": 11.4375,
|
| 93 |
+
"learning_rate": 4.4e-06,
|
| 94 |
+
"loss": 1.7068,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.031098153547133137,
|
| 99 |
+
"grad_norm": 11.75,
|
| 100 |
+
"learning_rate": 4.800000000000001e-06,
|
| 101 |
+
"loss": 1.688,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.03368966634272757,
|
| 106 |
+
"grad_norm": 11.6875,
|
| 107 |
+
"learning_rate": 5.2e-06,
|
| 108 |
+
"loss": 1.6602,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.036281179138321996,
|
| 113 |
+
"grad_norm": 11.5625,
|
| 114 |
+
"learning_rate": 5.600000000000001e-06,
|
| 115 |
+
"loss": 1.6389,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.038872691933916424,
|
| 120 |
+
"grad_norm": 10.75,
|
| 121 |
+
"learning_rate": 6e-06,
|
| 122 |
+
"loss": 1.6228,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.04146420472951085,
|
| 127 |
+
"grad_norm": 10.8125,
|
| 128 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 129 |
+
"loss": 1.5823,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.04405571752510528,
|
| 134 |
+
"grad_norm": 9.5625,
|
| 135 |
+
"learning_rate": 6.800000000000001e-06,
|
| 136 |
+
"loss": 1.5134,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.04664723032069971,
|
| 141 |
+
"grad_norm": 9.125,
|
| 142 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 143 |
+
"loss": 1.4833,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.049238743116294136,
|
| 148 |
+
"grad_norm": 7.375,
|
| 149 |
+
"learning_rate": 7.600000000000001e-06,
|
| 150 |
+
"loss": 1.4966,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.05183025591188856,
|
| 155 |
+
"grad_norm": 7.0,
|
| 156 |
+
"learning_rate": 8.000000000000001e-06,
|
| 157 |
+
"loss": 1.4653,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.05183025591188856,
|
| 162 |
+
"eval_loss": 1.4041186571121216,
|
| 163 |
+
"eval_model_preparation_time": 0.0003,
|
| 164 |
+
"eval_runtime": 24.6226,
|
| 165 |
+
"eval_samples_per_second": 105.716,
|
| 166 |
+
"eval_steps_per_second": 13.24,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.05442176870748299,
|
| 171 |
+
"grad_norm": 6.0625,
|
| 172 |
+
"learning_rate": 8.400000000000001e-06,
|
| 173 |
+
"loss": 1.3844,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.05701328150307742,
|
| 178 |
+
"grad_norm": 5.375,
|
| 179 |
+
"learning_rate": 8.8e-06,
|
| 180 |
+
"loss": 1.3735,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05960479429867185,
|
| 185 |
+
"grad_norm": 5.09375,
|
| 186 |
+
"learning_rate": 9.200000000000002e-06,
|
| 187 |
+
"loss": 1.3281,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.062196307094266275,
|
| 192 |
+
"grad_norm": 5.25,
|
| 193 |
+
"learning_rate": 9.600000000000001e-06,
|
| 194 |
+
"loss": 1.2837,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.06478781988986071,
|
| 199 |
+
"grad_norm": 5.25,
|
| 200 |
+
"learning_rate": 1e-05,
|
| 201 |
+
"loss": 1.2777,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.06737933268545514,
|
| 206 |
+
"grad_norm": 5.03125,
|
| 207 |
+
"learning_rate": 1.04e-05,
|
| 208 |
+
"loss": 1.2465,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.06997084548104957,
|
| 213 |
+
"grad_norm": 5.0625,
|
| 214 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 215 |
+
"loss": 1.2041,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.07256235827664399,
|
| 220 |
+
"grad_norm": 4.9375,
|
| 221 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 222 |
+
"loss": 1.1524,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.07515387107223842,
|
| 227 |
+
"grad_norm": 4.65625,
|
| 228 |
+
"learning_rate": 1.16e-05,
|
| 229 |
+
"loss": 1.1491,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.07774538386783285,
|
| 234 |
+
"grad_norm": 5.125,
|
| 235 |
+
"learning_rate": 1.2e-05,
|
| 236 |
+
"loss": 1.127,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.07774538386783285,
|
| 241 |
+
"eval_loss": 1.105301856994629,
|
| 242 |
+
"eval_model_preparation_time": 0.0003,
|
| 243 |
+
"eval_runtime": 24.5195,
|
| 244 |
+
"eval_samples_per_second": 106.161,
|
| 245 |
+
"eval_steps_per_second": 13.296,
|
| 246 |
+
"step": 30
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.08033689666342728,
|
| 250 |
+
"grad_norm": 5.09375,
|
| 251 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 252 |
+
"loss": 1.0993,
|
| 253 |
+
"step": 31
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.0829284094590217,
|
| 257 |
+
"grad_norm": 4.9375,
|
| 258 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 259 |
+
"loss": 1.0637,
|
| 260 |
+
"step": 32
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.08551992225461613,
|
| 264 |
+
"grad_norm": 4.75,
|
| 265 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 266 |
+
"loss": 1.0447,
|
| 267 |
+
"step": 33
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.08811143505021056,
|
| 271 |
+
"grad_norm": 5.21875,
|
| 272 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 273 |
+
"loss": 1.047,
|
| 274 |
+
"step": 34
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.09070294784580499,
|
| 278 |
+
"grad_norm": 4.9375,
|
| 279 |
+
"learning_rate": 1.4e-05,
|
| 280 |
+
"loss": 0.9841,
|
| 281 |
+
"step": 35
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.09329446064139942,
|
| 285 |
+
"grad_norm": 4.90625,
|
| 286 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 287 |
+
"loss": 0.9735,
|
| 288 |
+
"step": 36
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.09588597343699384,
|
| 292 |
+
"grad_norm": 5.71875,
|
| 293 |
+
"learning_rate": 1.48e-05,
|
| 294 |
+
"loss": 0.9409,
|
| 295 |
+
"step": 37
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.09847748623258827,
|
| 299 |
+
"grad_norm": 5.0625,
|
| 300 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 301 |
+
"loss": 0.9108,
|
| 302 |
+
"step": 38
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.1010689990281827,
|
| 306 |
+
"grad_norm": 4.90625,
|
| 307 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 308 |
+
"loss": 0.9029,
|
| 309 |
+
"step": 39
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.10366051182377713,
|
| 313 |
+
"grad_norm": 5.0625,
|
| 314 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 315 |
+
"loss": 0.8938,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.10366051182377713,
|
| 320 |
+
"eval_loss": 0.8692858815193176,
|
| 321 |
+
"eval_model_preparation_time": 0.0003,
|
| 322 |
+
"eval_runtime": 24.5016,
|
| 323 |
+
"eval_samples_per_second": 106.238,
|
| 324 |
+
"eval_steps_per_second": 13.305,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.10625202461937155,
|
| 329 |
+
"grad_norm": 5.125,
|
| 330 |
+
"learning_rate": 1.64e-05,
|
| 331 |
+
"loss": 0.8501,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.10884353741496598,
|
| 336 |
+
"grad_norm": 4.53125,
|
| 337 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 338 |
+
"loss": 0.8545,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.11143505021056041,
|
| 343 |
+
"grad_norm": 5.1875,
|
| 344 |
+
"learning_rate": 1.72e-05,
|
| 345 |
+
"loss": 0.8169,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.11402656300615484,
|
| 350 |
+
"grad_norm": 4.5,
|
| 351 |
+
"learning_rate": 1.76e-05,
|
| 352 |
+
"loss": 0.8102,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.11661807580174927,
|
| 357 |
+
"grad_norm": 4.3125,
|
| 358 |
+
"learning_rate": 1.8e-05,
|
| 359 |
+
"loss": 0.8093,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.1192095885973437,
|
| 364 |
+
"grad_norm": 4.28125,
|
| 365 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 366 |
+
"loss": 0.7798,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.12180110139293812,
|
| 371 |
+
"grad_norm": 4.09375,
|
| 372 |
+
"learning_rate": 1.88e-05,
|
| 373 |
+
"loss": 0.7761,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.12439261418853255,
|
| 378 |
+
"grad_norm": 4.125,
|
| 379 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 380 |
+
"loss": 0.7647,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.12698412698412698,
|
| 385 |
+
"grad_norm": 3.765625,
|
| 386 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 387 |
+
"loss": 0.7612,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.12957563977972142,
|
| 392 |
+
"grad_norm": 4.0,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.7498,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.12957563977972142,
|
| 399 |
+
"eval_loss": 0.744697093963623,
|
| 400 |
+
"eval_model_preparation_time": 0.0003,
|
| 401 |
+
"eval_runtime": 24.6181,
|
| 402 |
+
"eval_samples_per_second": 105.735,
|
| 403 |
+
"eval_steps_per_second": 13.242,
|
| 404 |
+
"step": 50
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.13216715257531583,
|
| 408 |
+
"grad_norm": 4.5,
|
| 409 |
+
"learning_rate": 1.9999560279257315e-05,
|
| 410 |
+
"loss": 0.7504,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.13475866537091027,
|
| 415 |
+
"grad_norm": 3.796875,
|
| 416 |
+
"learning_rate": 1.999824115570012e-05,
|
| 417 |
+
"loss": 0.7181,
|
| 418 |
+
"step": 52
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.1373501781665047,
|
| 422 |
+
"grad_norm": 3.703125,
|
| 423 |
+
"learning_rate": 1.9996042745337617e-05,
|
| 424 |
+
"loss": 0.7195,
|
| 425 |
+
"step": 53
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.13994169096209913,
|
| 429 |
+
"grad_norm": 3.921875,
|
| 430 |
+
"learning_rate": 1.999296524150713e-05,
|
| 431 |
+
"loss": 0.7232,
|
| 432 |
+
"step": 54
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.14253320375769354,
|
| 436 |
+
"grad_norm": 3.6875,
|
| 437 |
+
"learning_rate": 1.9989008914857115e-05,
|
| 438 |
+
"loss": 0.725,
|
| 439 |
+
"step": 55
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.14512471655328799,
|
| 443 |
+
"grad_norm": 3.734375,
|
| 444 |
+
"learning_rate": 1.9984174113323352e-05,
|
| 445 |
+
"loss": 0.6972,
|
| 446 |
+
"step": 56
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.1477162293488824,
|
| 450 |
+
"grad_norm": 3.5,
|
| 451 |
+
"learning_rate": 1.9978461262098342e-05,
|
| 452 |
+
"loss": 0.6792,
|
| 453 |
+
"step": 57
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.15030774214447684,
|
| 457 |
+
"grad_norm": 4.0625,
|
| 458 |
+
"learning_rate": 1.9971870863593924e-05,
|
| 459 |
+
"loss": 0.7192,
|
| 460 |
+
"step": 58
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.15289925494007126,
|
| 464 |
+
"grad_norm": 3.75,
|
| 465 |
+
"learning_rate": 1.9964403497397086e-05,
|
| 466 |
+
"loss": 0.7107,
|
| 467 |
+
"step": 59
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1554907677356657,
|
| 471 |
+
"grad_norm": 3.953125,
|
| 472 |
+
"learning_rate": 1.9956059820218982e-05,
|
| 473 |
+
"loss": 0.6866,
|
| 474 |
+
"step": 60
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.1554907677356657,
|
| 478 |
+
"eval_loss": 0.6849498152732849,
|
| 479 |
+
"eval_model_preparation_time": 0.0003,
|
| 480 |
+
"eval_runtime": 24.5203,
|
| 481 |
+
"eval_samples_per_second": 106.157,
|
| 482 |
+
"eval_steps_per_second": 13.295,
|
| 483 |
+
"step": 60
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.1580822805312601,
|
| 487 |
+
"grad_norm": 3.953125,
|
| 488 |
+
"learning_rate": 1.9946840565837206e-05,
|
| 489 |
+
"loss": 0.6818,
|
| 490 |
+
"step": 61
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.16067379332685455,
|
| 494 |
+
"grad_norm": 3.546875,
|
| 495 |
+
"learning_rate": 1.9936746545031225e-05,
|
| 496 |
+
"loss": 0.6855,
|
| 497 |
+
"step": 62
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.16326530612244897,
|
| 501 |
+
"grad_norm": 3.359375,
|
| 502 |
+
"learning_rate": 1.9925778645511112e-05,
|
| 503 |
+
"loss": 0.6799,
|
| 504 |
+
"step": 63
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.1658568189180434,
|
| 508 |
+
"grad_norm": 3.828125,
|
| 509 |
+
"learning_rate": 1.991393783183945e-05,
|
| 510 |
+
"loss": 0.6719,
|
| 511 |
+
"step": 64
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.16844833171363785,
|
| 515 |
+
"grad_norm": 3.0,
|
| 516 |
+
"learning_rate": 1.990122514534651e-05,
|
| 517 |
+
"loss": 0.66,
|
| 518 |
+
"step": 65
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.17103984450923226,
|
| 522 |
+
"grad_norm": 2.96875,
|
| 523 |
+
"learning_rate": 1.988764170403869e-05,
|
| 524 |
+
"loss": 0.6718,
|
| 525 |
+
"step": 66
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.1736313573048267,
|
| 529 |
+
"grad_norm": 3.15625,
|
| 530 |
+
"learning_rate": 1.9873188702500163e-05,
|
| 531 |
+
"loss": 0.6661,
|
| 532 |
+
"step": 67
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.17622287010042112,
|
| 536 |
+
"grad_norm": 2.828125,
|
| 537 |
+
"learning_rate": 1.9857867411787847e-05,
|
| 538 |
+
"loss": 0.6523,
|
| 539 |
+
"step": 68
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.17881438289601556,
|
| 543 |
+
"grad_norm": 3.203125,
|
| 544 |
+
"learning_rate": 1.9841679179319605e-05,
|
| 545 |
+
"loss": 0.6494,
|
| 546 |
+
"step": 69
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.18140589569160998,
|
| 550 |
+
"grad_norm": 2.875,
|
| 551 |
+
"learning_rate": 1.982462542875576e-05,
|
| 552 |
+
"loss": 0.6411,
|
| 553 |
+
"step": 70
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.18140589569160998,
|
| 557 |
+
"eval_loss": 0.6511064171791077,
|
| 558 |
+
"eval_model_preparation_time": 0.0003,
|
| 559 |
+
"eval_runtime": 24.5304,
|
| 560 |
+
"eval_samples_per_second": 106.113,
|
| 561 |
+
"eval_steps_per_second": 13.29,
|
| 562 |
+
"step": 70
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.18399740848720442,
|
| 566 |
+
"grad_norm": 3.296875,
|
| 567 |
+
"learning_rate": 1.9806707659873886e-05,
|
| 568 |
+
"loss": 0.6463,
|
| 569 |
+
"step": 71
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.18658892128279883,
|
| 573 |
+
"grad_norm": 3.0625,
|
| 574 |
+
"learning_rate": 1.9787927448436913e-05,
|
| 575 |
+
"loss": 0.6375,
|
| 576 |
+
"step": 72
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.18918043407839327,
|
| 580 |
+
"grad_norm": 2.75,
|
| 581 |
+
"learning_rate": 1.9768286446054533e-05,
|
| 582 |
+
"loss": 0.6386,
|
| 583 |
+
"step": 73
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.1917719468739877,
|
| 587 |
+
"grad_norm": 2.875,
|
| 588 |
+
"learning_rate": 1.974778638003799e-05,
|
| 589 |
+
"loss": 0.6368,
|
| 590 |
+
"step": 74
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.19436345966958213,
|
| 594 |
+
"grad_norm": 2.953125,
|
| 595 |
+
"learning_rate": 1.972642905324813e-05,
|
| 596 |
+
"loss": 0.6271,
|
| 597 |
+
"step": 75
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.19695497246517654,
|
| 601 |
+
"grad_norm": 2.921875,
|
| 602 |
+
"learning_rate": 1.9704216343936875e-05,
|
| 603 |
+
"loss": 0.6501,
|
| 604 |
+
"step": 76
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.19954648526077098,
|
| 608 |
+
"grad_norm": 3.015625,
|
| 609 |
+
"learning_rate": 1.9681150205582025e-05,
|
| 610 |
+
"loss": 0.6111,
|
| 611 |
+
"step": 77
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2021379980563654,
|
| 615 |
+
"grad_norm": 3.171875,
|
| 616 |
+
"learning_rate": 1.9657232666715485e-05,
|
| 617 |
+
"loss": 0.651,
|
| 618 |
+
"step": 78
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.20472951085195984,
|
| 622 |
+
"grad_norm": 3.0625,
|
| 623 |
+
"learning_rate": 1.9632465830744846e-05,
|
| 624 |
+
"loss": 0.6184,
|
| 625 |
+
"step": 79
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.20732102364755425,
|
| 629 |
+
"grad_norm": 3.25,
|
| 630 |
+
"learning_rate": 1.9606851875768404e-05,
|
| 631 |
+
"loss": 0.6259,
|
| 632 |
+
"step": 80
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20732102364755425,
|
| 636 |
+
"eval_loss": 0.6278263330459595,
|
| 637 |
+
"eval_model_preparation_time": 0.0003,
|
| 638 |
+
"eval_runtime": 24.4892,
|
| 639 |
+
"eval_samples_per_second": 106.292,
|
| 640 |
+
"eval_steps_per_second": 13.312,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2099125364431487,
|
| 645 |
+
"grad_norm": 2.875,
|
| 646 |
+
"learning_rate": 1.9580393054383622e-05,
|
| 647 |
+
"loss": 0.6288,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2125040492387431,
|
| 652 |
+
"grad_norm": 3.359375,
|
| 653 |
+
"learning_rate": 1.9553091693489018e-05,
|
| 654 |
+
"loss": 0.6403,
|
| 655 |
+
"step": 82
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.21509556203433755,
|
| 659 |
+
"grad_norm": 2.921875,
|
| 660 |
+
"learning_rate": 1.9524950194079534e-05,
|
| 661 |
+
"loss": 0.621,
|
| 662 |
+
"step": 83
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.21768707482993196,
|
| 666 |
+
"grad_norm": 2.84375,
|
| 667 |
+
"learning_rate": 1.9495971031035367e-05,
|
| 668 |
+
"loss": 0.6135,
|
| 669 |
+
"step": 84
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.2202785876255264,
|
| 673 |
+
"grad_norm": 2.921875,
|
| 674 |
+
"learning_rate": 1.9466156752904344e-05,
|
| 675 |
+
"loss": 0.6211,
|
| 676 |
+
"step": 85
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.22287010042112082,
|
| 680 |
+
"grad_norm": 3.109375,
|
| 681 |
+
"learning_rate": 1.9435509981677764e-05,
|
| 682 |
+
"loss": 0.6198,
|
| 683 |
+
"step": 86
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.22546161321671526,
|
| 687 |
+
"grad_norm": 2.625,
|
| 688 |
+
"learning_rate": 1.9404033412559828e-05,
|
| 689 |
+
"loss": 0.5972,
|
| 690 |
+
"step": 87
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.22805312601230968,
|
| 694 |
+
"grad_norm": 3.0,
|
| 695 |
+
"learning_rate": 1.9371729813730606e-05,
|
| 696 |
+
"loss": 0.614,
|
| 697 |
+
"step": 88
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.23064463880790412,
|
| 701 |
+
"grad_norm": 2.75,
|
| 702 |
+
"learning_rate": 1.9338602026102594e-05,
|
| 703 |
+
"loss": 0.5998,
|
| 704 |
+
"step": 89
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.23323615160349853,
|
| 708 |
+
"grad_norm": 2.796875,
|
| 709 |
+
"learning_rate": 1.9304652963070868e-05,
|
| 710 |
+
"loss": 0.6181,
|
| 711 |
+
"step": 90
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.23323615160349853,
|
| 715 |
+
"eval_loss": 0.6108965277671814,
|
| 716 |
+
"eval_model_preparation_time": 0.0003,
|
| 717 |
+
"eval_runtime": 24.4982,
|
| 718 |
+
"eval_samples_per_second": 106.253,
|
| 719 |
+
"eval_steps_per_second": 13.307,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.23582766439909297,
|
| 724 |
+
"grad_norm": 2.8125,
|
| 725 |
+
"learning_rate": 1.9269885610256866e-05,
|
| 726 |
+
"loss": 0.6059,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2384191771946874,
|
| 731 |
+
"grad_norm": 2.734375,
|
| 732 |
+
"learning_rate": 1.9234303025245835e-05,
|
| 733 |
+
"loss": 0.6165,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.24101068999028183,
|
| 738 |
+
"grad_norm": 2.984375,
|
| 739 |
+
"learning_rate": 1.919790833731791e-05,
|
| 740 |
+
"loss": 0.6241,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.24360220278587624,
|
| 745 |
+
"grad_norm": 3.015625,
|
| 746 |
+
"learning_rate": 1.9160704747172935e-05,
|
| 747 |
+
"loss": 0.5913,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.24619371558147068,
|
| 752 |
+
"grad_norm": 2.84375,
|
| 753 |
+
"learning_rate": 1.9122695526648968e-05,
|
| 754 |
+
"loss": 0.585,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.2487852283770651,
|
| 759 |
+
"grad_norm": 3.484375,
|
| 760 |
+
"learning_rate": 1.9083884018434545e-05,
|
| 761 |
+
"loss": 0.5897,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.2513767411726595,
|
| 766 |
+
"grad_norm": 2.84375,
|
| 767 |
+
"learning_rate": 1.9044273635774707e-05,
|
| 768 |
+
"loss": 0.6032,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.25396825396825395,
|
| 773 |
+
"grad_norm": 2.75,
|
| 774 |
+
"learning_rate": 1.900386786217083e-05,
|
| 775 |
+
"loss": 0.594,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.2565597667638484,
|
| 780 |
+
"grad_norm": 2.8125,
|
| 781 |
+
"learning_rate": 1.8962670251074276e-05,
|
| 782 |
+
"loss": 0.5958,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.25915127955944284,
|
| 787 |
+
"grad_norm": 2.65625,
|
| 788 |
+
"learning_rate": 1.8920684425573865e-05,
|
| 789 |
+
"loss": 0.5821,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.25915127955944284,
|
| 794 |
+
"eval_loss": 0.5988509058952332,
|
| 795 |
+
"eval_model_preparation_time": 0.0003,
|
| 796 |
+
"eval_runtime": 24.4884,
|
| 797 |
+
"eval_samples_per_second": 106.295,
|
| 798 |
+
"eval_steps_per_second": 13.312,
|
| 799 |
+
"step": 100
|
| 800 |
+
}
|
| 801 |
+
],
|
| 802 |
+
"logging_steps": 1,
|
| 803 |
+
"max_steps": 385,
|
| 804 |
+
"num_input_tokens_seen": 0,
|
| 805 |
+
"num_train_epochs": 1,
|
| 806 |
+
"save_steps": 100,
|
| 807 |
+
"stateful_callbacks": {
|
| 808 |
+
"TrainerControl": {
|
| 809 |
+
"args": {
|
| 810 |
+
"should_epoch_stop": false,
|
| 811 |
+
"should_evaluate": false,
|
| 812 |
+
"should_log": false,
|
| 813 |
+
"should_save": true,
|
| 814 |
+
"should_training_stop": false
|
| 815 |
+
},
|
| 816 |
+
"attributes": {}
|
| 817 |
+
}
|
| 818 |
+
},
|
| 819 |
+
"total_flos": 2.7825750933504e+16,
|
| 820 |
+
"train_batch_size": 8,
|
| 821 |
+
"trial_name": null,
|
| 822 |
+
"trial_params": null
|
| 823 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca15ebb16a59dc055f8ae01b1eb1038e869a6556aa3b7b802c58f2dde6a2993c
|
| 3 |
+
size 5304
|
checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322b2d3fc9de58487c02f1cd651d484d73244f9704de3d5feea36d002a38af0f
|
| 3 |
+
size 748
|
checkpoint-200/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82bdd024a0ba026e4001e0433d3922a27b1242913db7be87e2851d17165b99c8
|
| 3 |
+
size 111
|
checkpoint-200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7097f484aaede8efd96df5361bf11991048535719a9ece45a6160bf49c0121f9
|
| 3 |
+
size 810702192
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1891d4f0cfe566e718551469717420b08c3f586a4a837b4d47c08a779b670fc
|
| 3 |
+
size 1621580026
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad5da87704f9496a4cad943d2aa8988a987b1e77b57fa4a28ff4c89ee480ac0
|
| 3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5efd9b5f266aeac292c1c263af3ec67abbe75dee3425023232f2c488a9f2e17e
|
| 3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8
|
| 3 |
+
size 473
|
checkpoint-200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870f4e2baa6b683221fa52004d5d6f40ab8c9d31961617304b78c910c2c3caf2
|
| 3 |
+
size 2114042
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c4f587ac3a67c3964d3e84248f95ffc8e4f0e64d9de677692df39aa35eb2d11
|
| 3 |
+
size 4845
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,1613 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5183025591188857,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0025915127955944283,
|
| 13 |
+
"grad_norm": 12.625,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.7977,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0051830255911888565,
|
| 20 |
+
"grad_norm": 12.0625,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.7787,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.007774538386783284,
|
| 27 |
+
"grad_norm": 13.0,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.8003,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.010366051182377713,
|
| 34 |
+
"grad_norm": 12.5625,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.787,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01295756397797214,
|
| 41 |
+
"grad_norm": 12.25,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.7684,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.015549076773566569,
|
| 48 |
+
"grad_norm": 12.625,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.7544,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.018140589569160998,
|
| 55 |
+
"grad_norm": 12.5,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.7769,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.020732102364755426,
|
| 62 |
+
"grad_norm": 11.4375,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.7161,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.023323615160349854,
|
| 69 |
+
"grad_norm": 11.5,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.7165,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02591512795594428,
|
| 76 |
+
"grad_norm": 12.1875,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.7437,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02591512795594428,
|
| 83 |
+
"eval_loss": 1.7256978750228882,
|
| 84 |
+
"eval_model_preparation_time": 0.0003,
|
| 85 |
+
"eval_runtime": 24.5814,
|
| 86 |
+
"eval_samples_per_second": 105.893,
|
| 87 |
+
"eval_steps_per_second": 13.262,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.02850664075153871,
|
| 92 |
+
"grad_norm": 11.4375,
|
| 93 |
+
"learning_rate": 4.4e-06,
|
| 94 |
+
"loss": 1.7068,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.031098153547133137,
|
| 99 |
+
"grad_norm": 11.75,
|
| 100 |
+
"learning_rate": 4.800000000000001e-06,
|
| 101 |
+
"loss": 1.688,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.03368966634272757,
|
| 106 |
+
"grad_norm": 11.6875,
|
| 107 |
+
"learning_rate": 5.2e-06,
|
| 108 |
+
"loss": 1.6602,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.036281179138321996,
|
| 113 |
+
"grad_norm": 11.5625,
|
| 114 |
+
"learning_rate": 5.600000000000001e-06,
|
| 115 |
+
"loss": 1.6389,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.038872691933916424,
|
| 120 |
+
"grad_norm": 10.75,
|
| 121 |
+
"learning_rate": 6e-06,
|
| 122 |
+
"loss": 1.6228,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.04146420472951085,
|
| 127 |
+
"grad_norm": 10.8125,
|
| 128 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 129 |
+
"loss": 1.5823,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.04405571752510528,
|
| 134 |
+
"grad_norm": 9.5625,
|
| 135 |
+
"learning_rate": 6.800000000000001e-06,
|
| 136 |
+
"loss": 1.5134,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.04664723032069971,
|
| 141 |
+
"grad_norm": 9.125,
|
| 142 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 143 |
+
"loss": 1.4833,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.049238743116294136,
|
| 148 |
+
"grad_norm": 7.375,
|
| 149 |
+
"learning_rate": 7.600000000000001e-06,
|
| 150 |
+
"loss": 1.4966,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.05183025591188856,
|
| 155 |
+
"grad_norm": 7.0,
|
| 156 |
+
"learning_rate": 8.000000000000001e-06,
|
| 157 |
+
"loss": 1.4653,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.05183025591188856,
|
| 162 |
+
"eval_loss": 1.4041186571121216,
|
| 163 |
+
"eval_model_preparation_time": 0.0003,
|
| 164 |
+
"eval_runtime": 24.6226,
|
| 165 |
+
"eval_samples_per_second": 105.716,
|
| 166 |
+
"eval_steps_per_second": 13.24,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.05442176870748299,
|
| 171 |
+
"grad_norm": 6.0625,
|
| 172 |
+
"learning_rate": 8.400000000000001e-06,
|
| 173 |
+
"loss": 1.3844,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.05701328150307742,
|
| 178 |
+
"grad_norm": 5.375,
|
| 179 |
+
"learning_rate": 8.8e-06,
|
| 180 |
+
"loss": 1.3735,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05960479429867185,
|
| 185 |
+
"grad_norm": 5.09375,
|
| 186 |
+
"learning_rate": 9.200000000000002e-06,
|
| 187 |
+
"loss": 1.3281,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.062196307094266275,
|
| 192 |
+
"grad_norm": 5.25,
|
| 193 |
+
"learning_rate": 9.600000000000001e-06,
|
| 194 |
+
"loss": 1.2837,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.06478781988986071,
|
| 199 |
+
"grad_norm": 5.25,
|
| 200 |
+
"learning_rate": 1e-05,
|
| 201 |
+
"loss": 1.2777,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.06737933268545514,
|
| 206 |
+
"grad_norm": 5.03125,
|
| 207 |
+
"learning_rate": 1.04e-05,
|
| 208 |
+
"loss": 1.2465,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.06997084548104957,
|
| 213 |
+
"grad_norm": 5.0625,
|
| 214 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 215 |
+
"loss": 1.2041,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.07256235827664399,
|
| 220 |
+
"grad_norm": 4.9375,
|
| 221 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 222 |
+
"loss": 1.1524,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.07515387107223842,
|
| 227 |
+
"grad_norm": 4.65625,
|
| 228 |
+
"learning_rate": 1.16e-05,
|
| 229 |
+
"loss": 1.1491,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.07774538386783285,
|
| 234 |
+
"grad_norm": 5.125,
|
| 235 |
+
"learning_rate": 1.2e-05,
|
| 236 |
+
"loss": 1.127,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.07774538386783285,
|
| 241 |
+
"eval_loss": 1.105301856994629,
|
| 242 |
+
"eval_model_preparation_time": 0.0003,
|
| 243 |
+
"eval_runtime": 24.5195,
|
| 244 |
+
"eval_samples_per_second": 106.161,
|
| 245 |
+
"eval_steps_per_second": 13.296,
|
| 246 |
+
"step": 30
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.08033689666342728,
|
| 250 |
+
"grad_norm": 5.09375,
|
| 251 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 252 |
+
"loss": 1.0993,
|
| 253 |
+
"step": 31
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.0829284094590217,
|
| 257 |
+
"grad_norm": 4.9375,
|
| 258 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 259 |
+
"loss": 1.0637,
|
| 260 |
+
"step": 32
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.08551992225461613,
|
| 264 |
+
"grad_norm": 4.75,
|
| 265 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 266 |
+
"loss": 1.0447,
|
| 267 |
+
"step": 33
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.08811143505021056,
|
| 271 |
+
"grad_norm": 5.21875,
|
| 272 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 273 |
+
"loss": 1.047,
|
| 274 |
+
"step": 34
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.09070294784580499,
|
| 278 |
+
"grad_norm": 4.9375,
|
| 279 |
+
"learning_rate": 1.4e-05,
|
| 280 |
+
"loss": 0.9841,
|
| 281 |
+
"step": 35
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.09329446064139942,
|
| 285 |
+
"grad_norm": 4.90625,
|
| 286 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 287 |
+
"loss": 0.9735,
|
| 288 |
+
"step": 36
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.09588597343699384,
|
| 292 |
+
"grad_norm": 5.71875,
|
| 293 |
+
"learning_rate": 1.48e-05,
|
| 294 |
+
"loss": 0.9409,
|
| 295 |
+
"step": 37
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.09847748623258827,
|
| 299 |
+
"grad_norm": 5.0625,
|
| 300 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 301 |
+
"loss": 0.9108,
|
| 302 |
+
"step": 38
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.1010689990281827,
|
| 306 |
+
"grad_norm": 4.90625,
|
| 307 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 308 |
+
"loss": 0.9029,
|
| 309 |
+
"step": 39
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.10366051182377713,
|
| 313 |
+
"grad_norm": 5.0625,
|
| 314 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 315 |
+
"loss": 0.8938,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.10366051182377713,
|
| 320 |
+
"eval_loss": 0.8692858815193176,
|
| 321 |
+
"eval_model_preparation_time": 0.0003,
|
| 322 |
+
"eval_runtime": 24.5016,
|
| 323 |
+
"eval_samples_per_second": 106.238,
|
| 324 |
+
"eval_steps_per_second": 13.305,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.10625202461937155,
|
| 329 |
+
"grad_norm": 5.125,
|
| 330 |
+
"learning_rate": 1.64e-05,
|
| 331 |
+
"loss": 0.8501,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.10884353741496598,
|
| 336 |
+
"grad_norm": 4.53125,
|
| 337 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 338 |
+
"loss": 0.8545,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.11143505021056041,
|
| 343 |
+
"grad_norm": 5.1875,
|
| 344 |
+
"learning_rate": 1.72e-05,
|
| 345 |
+
"loss": 0.8169,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.11402656300615484,
|
| 350 |
+
"grad_norm": 4.5,
|
| 351 |
+
"learning_rate": 1.76e-05,
|
| 352 |
+
"loss": 0.8102,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.11661807580174927,
|
| 357 |
+
"grad_norm": 4.3125,
|
| 358 |
+
"learning_rate": 1.8e-05,
|
| 359 |
+
"loss": 0.8093,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.1192095885973437,
|
| 364 |
+
"grad_norm": 4.28125,
|
| 365 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 366 |
+
"loss": 0.7798,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.12180110139293812,
|
| 371 |
+
"grad_norm": 4.09375,
|
| 372 |
+
"learning_rate": 1.88e-05,
|
| 373 |
+
"loss": 0.7761,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.12439261418853255,
|
| 378 |
+
"grad_norm": 4.125,
|
| 379 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 380 |
+
"loss": 0.7647,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.12698412698412698,
|
| 385 |
+
"grad_norm": 3.765625,
|
| 386 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 387 |
+
"loss": 0.7612,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.12957563977972142,
|
| 392 |
+
"grad_norm": 4.0,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.7498,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.12957563977972142,
|
| 399 |
+
"eval_loss": 0.744697093963623,
|
| 400 |
+
"eval_model_preparation_time": 0.0003,
|
| 401 |
+
"eval_runtime": 24.6181,
|
| 402 |
+
"eval_samples_per_second": 105.735,
|
| 403 |
+
"eval_steps_per_second": 13.242,
|
| 404 |
+
"step": 50
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.13216715257531583,
|
| 408 |
+
"grad_norm": 4.5,
|
| 409 |
+
"learning_rate": 1.9999560279257315e-05,
|
| 410 |
+
"loss": 0.7504,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.13475866537091027,
|
| 415 |
+
"grad_norm": 3.796875,
|
| 416 |
+
"learning_rate": 1.999824115570012e-05,
|
| 417 |
+
"loss": 0.7181,
|
| 418 |
+
"step": 52
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.1373501781665047,
|
| 422 |
+
"grad_norm": 3.703125,
|
| 423 |
+
"learning_rate": 1.9996042745337617e-05,
|
| 424 |
+
"loss": 0.7195,
|
| 425 |
+
"step": 53
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.13994169096209913,
|
| 429 |
+
"grad_norm": 3.921875,
|
| 430 |
+
"learning_rate": 1.999296524150713e-05,
|
| 431 |
+
"loss": 0.7232,
|
| 432 |
+
"step": 54
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.14253320375769354,
|
| 436 |
+
"grad_norm": 3.6875,
|
| 437 |
+
"learning_rate": 1.9989008914857115e-05,
|
| 438 |
+
"loss": 0.725,
|
| 439 |
+
"step": 55
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.14512471655328799,
|
| 443 |
+
"grad_norm": 3.734375,
|
| 444 |
+
"learning_rate": 1.9984174113323352e-05,
|
| 445 |
+
"loss": 0.6972,
|
| 446 |
+
"step": 56
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.1477162293488824,
|
| 450 |
+
"grad_norm": 3.5,
|
| 451 |
+
"learning_rate": 1.9978461262098342e-05,
|
| 452 |
+
"loss": 0.6792,
|
| 453 |
+
"step": 57
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.15030774214447684,
|
| 457 |
+
"grad_norm": 4.0625,
|
| 458 |
+
"learning_rate": 1.9971870863593924e-05,
|
| 459 |
+
"loss": 0.7192,
|
| 460 |
+
"step": 58
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.15289925494007126,
|
| 464 |
+
"grad_norm": 3.75,
|
| 465 |
+
"learning_rate": 1.9964403497397086e-05,
|
| 466 |
+
"loss": 0.7107,
|
| 467 |
+
"step": 59
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1554907677356657,
|
| 471 |
+
"grad_norm": 3.953125,
|
| 472 |
+
"learning_rate": 1.9956059820218982e-05,
|
| 473 |
+
"loss": 0.6866,
|
| 474 |
+
"step": 60
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.1554907677356657,
|
| 478 |
+
"eval_loss": 0.6849498152732849,
|
| 479 |
+
"eval_model_preparation_time": 0.0003,
|
| 480 |
+
"eval_runtime": 24.5203,
|
| 481 |
+
"eval_samples_per_second": 106.157,
|
| 482 |
+
"eval_steps_per_second": 13.295,
|
| 483 |
+
"step": 60
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.1580822805312601,
|
| 487 |
+
"grad_norm": 3.953125,
|
| 488 |
+
"learning_rate": 1.9946840565837206e-05,
|
| 489 |
+
"loss": 0.6818,
|
| 490 |
+
"step": 61
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.16067379332685455,
|
| 494 |
+
"grad_norm": 3.546875,
|
| 495 |
+
"learning_rate": 1.9936746545031225e-05,
|
| 496 |
+
"loss": 0.6855,
|
| 497 |
+
"step": 62
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.16326530612244897,
|
| 501 |
+
"grad_norm": 3.359375,
|
| 502 |
+
"learning_rate": 1.9925778645511112e-05,
|
| 503 |
+
"loss": 0.6799,
|
| 504 |
+
"step": 63
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.1658568189180434,
|
| 508 |
+
"grad_norm": 3.828125,
|
| 509 |
+
"learning_rate": 1.991393783183945e-05,
|
| 510 |
+
"loss": 0.6719,
|
| 511 |
+
"step": 64
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.16844833171363785,
|
| 515 |
+
"grad_norm": 3.0,
|
| 516 |
+
"learning_rate": 1.990122514534651e-05,
|
| 517 |
+
"loss": 0.66,
|
| 518 |
+
"step": 65
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.17103984450923226,
|
| 522 |
+
"grad_norm": 2.96875,
|
| 523 |
+
"learning_rate": 1.988764170403869e-05,
|
| 524 |
+
"loss": 0.6718,
|
| 525 |
+
"step": 66
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.1736313573048267,
|
| 529 |
+
"grad_norm": 3.15625,
|
| 530 |
+
"learning_rate": 1.9873188702500163e-05,
|
| 531 |
+
"loss": 0.6661,
|
| 532 |
+
"step": 67
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.17622287010042112,
|
| 536 |
+
"grad_norm": 2.828125,
|
| 537 |
+
"learning_rate": 1.9857867411787847e-05,
|
| 538 |
+
"loss": 0.6523,
|
| 539 |
+
"step": 68
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.17881438289601556,
|
| 543 |
+
"grad_norm": 3.203125,
|
| 544 |
+
"learning_rate": 1.9841679179319605e-05,
|
| 545 |
+
"loss": 0.6494,
|
| 546 |
+
"step": 69
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.18140589569160998,
|
| 550 |
+
"grad_norm": 2.875,
|
| 551 |
+
"learning_rate": 1.982462542875576e-05,
|
| 552 |
+
"loss": 0.6411,
|
| 553 |
+
"step": 70
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.18140589569160998,
|
| 557 |
+
"eval_loss": 0.6511064171791077,
|
| 558 |
+
"eval_model_preparation_time": 0.0003,
|
| 559 |
+
"eval_runtime": 24.5304,
|
| 560 |
+
"eval_samples_per_second": 106.113,
|
| 561 |
+
"eval_steps_per_second": 13.29,
|
| 562 |
+
"step": 70
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.18399740848720442,
|
| 566 |
+
"grad_norm": 3.296875,
|
| 567 |
+
"learning_rate": 1.9806707659873886e-05,
|
| 568 |
+
"loss": 0.6463,
|
| 569 |
+
"step": 71
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.18658892128279883,
|
| 573 |
+
"grad_norm": 3.0625,
|
| 574 |
+
"learning_rate": 1.9787927448436913e-05,
|
| 575 |
+
"loss": 0.6375,
|
| 576 |
+
"step": 72
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.18918043407839327,
|
| 580 |
+
"grad_norm": 2.75,
|
| 581 |
+
"learning_rate": 1.9768286446054533e-05,
|
| 582 |
+
"loss": 0.6386,
|
| 583 |
+
"step": 73
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.1917719468739877,
|
| 587 |
+
"grad_norm": 2.875,
|
| 588 |
+
"learning_rate": 1.974778638003799e-05,
|
| 589 |
+
"loss": 0.6368,
|
| 590 |
+
"step": 74
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.19436345966958213,
|
| 594 |
+
"grad_norm": 2.953125,
|
| 595 |
+
"learning_rate": 1.972642905324813e-05,
|
| 596 |
+
"loss": 0.6271,
|
| 597 |
+
"step": 75
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.19695497246517654,
|
| 601 |
+
"grad_norm": 2.921875,
|
| 602 |
+
"learning_rate": 1.9704216343936875e-05,
|
| 603 |
+
"loss": 0.6501,
|
| 604 |
+
"step": 76
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.19954648526077098,
|
| 608 |
+
"grad_norm": 3.015625,
|
| 609 |
+
"learning_rate": 1.9681150205582025e-05,
|
| 610 |
+
"loss": 0.6111,
|
| 611 |
+
"step": 77
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2021379980563654,
|
| 615 |
+
"grad_norm": 3.171875,
|
| 616 |
+
"learning_rate": 1.9657232666715485e-05,
|
| 617 |
+
"loss": 0.651,
|
| 618 |
+
"step": 78
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.20472951085195984,
|
| 622 |
+
"grad_norm": 3.0625,
|
| 623 |
+
"learning_rate": 1.9632465830744846e-05,
|
| 624 |
+
"loss": 0.6184,
|
| 625 |
+
"step": 79
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.20732102364755425,
|
| 629 |
+
"grad_norm": 3.25,
|
| 630 |
+
"learning_rate": 1.9606851875768404e-05,
|
| 631 |
+
"loss": 0.6259,
|
| 632 |
+
"step": 80
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20732102364755425,
|
| 636 |
+
"eval_loss": 0.6278263330459595,
|
| 637 |
+
"eval_model_preparation_time": 0.0003,
|
| 638 |
+
"eval_runtime": 24.4892,
|
| 639 |
+
"eval_samples_per_second": 106.292,
|
| 640 |
+
"eval_steps_per_second": 13.312,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2099125364431487,
|
| 645 |
+
"grad_norm": 2.875,
|
| 646 |
+
"learning_rate": 1.9580393054383622e-05,
|
| 647 |
+
"loss": 0.6288,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2125040492387431,
|
| 652 |
+
"grad_norm": 3.359375,
|
| 653 |
+
"learning_rate": 1.9553091693489018e-05,
|
| 654 |
+
"loss": 0.6403,
|
| 655 |
+
"step": 82
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.21509556203433755,
|
| 659 |
+
"grad_norm": 2.921875,
|
| 660 |
+
"learning_rate": 1.9524950194079534e-05,
|
| 661 |
+
"loss": 0.621,
|
| 662 |
+
"step": 83
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.21768707482993196,
|
| 666 |
+
"grad_norm": 2.84375,
|
| 667 |
+
"learning_rate": 1.9495971031035367e-05,
|
| 668 |
+
"loss": 0.6135,
|
| 669 |
+
"step": 84
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.2202785876255264,
|
| 673 |
+
"grad_norm": 2.921875,
|
| 674 |
+
"learning_rate": 1.9466156752904344e-05,
|
| 675 |
+
"loss": 0.6211,
|
| 676 |
+
"step": 85
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.22287010042112082,
|
| 680 |
+
"grad_norm": 3.109375,
|
| 681 |
+
"learning_rate": 1.9435509981677764e-05,
|
| 682 |
+
"loss": 0.6198,
|
| 683 |
+
"step": 86
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.22546161321671526,
|
| 687 |
+
"grad_norm": 2.625,
|
| 688 |
+
"learning_rate": 1.9404033412559828e-05,
|
| 689 |
+
"loss": 0.5972,
|
| 690 |
+
"step": 87
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.22805312601230968,
|
| 694 |
+
"grad_norm": 3.0,
|
| 695 |
+
"learning_rate": 1.9371729813730606e-05,
|
| 696 |
+
"loss": 0.614,
|
| 697 |
+
"step": 88
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.23064463880790412,
|
| 701 |
+
"grad_norm": 2.75,
|
| 702 |
+
"learning_rate": 1.9338602026102594e-05,
|
| 703 |
+
"loss": 0.5998,
|
| 704 |
+
"step": 89
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.23323615160349853,
|
| 708 |
+
"grad_norm": 2.796875,
|
| 709 |
+
"learning_rate": 1.9304652963070868e-05,
|
| 710 |
+
"loss": 0.6181,
|
| 711 |
+
"step": 90
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.23323615160349853,
|
| 715 |
+
"eval_loss": 0.6108965277671814,
|
| 716 |
+
"eval_model_preparation_time": 0.0003,
|
| 717 |
+
"eval_runtime": 24.4982,
|
| 718 |
+
"eval_samples_per_second": 106.253,
|
| 719 |
+
"eval_steps_per_second": 13.307,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.23582766439909297,
|
| 724 |
+
"grad_norm": 2.8125,
|
| 725 |
+
"learning_rate": 1.9269885610256866e-05,
|
| 726 |
+
"loss": 0.6059,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2384191771946874,
|
| 731 |
+
"grad_norm": 2.734375,
|
| 732 |
+
"learning_rate": 1.9234303025245835e-05,
|
| 733 |
+
"loss": 0.6165,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.24101068999028183,
|
| 738 |
+
"grad_norm": 2.984375,
|
| 739 |
+
"learning_rate": 1.919790833731791e-05,
|
| 740 |
+
"loss": 0.6241,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.24360220278587624,
|
| 745 |
+
"grad_norm": 3.015625,
|
| 746 |
+
"learning_rate": 1.9160704747172935e-05,
|
| 747 |
+
"loss": 0.5913,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.24619371558147068,
|
| 752 |
+
"grad_norm": 2.84375,
|
| 753 |
+
"learning_rate": 1.9122695526648968e-05,
|
| 754 |
+
"loss": 0.585,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.2487852283770651,
|
| 759 |
+
"grad_norm": 3.484375,
|
| 760 |
+
"learning_rate": 1.9083884018434545e-05,
|
| 761 |
+
"loss": 0.5897,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.2513767411726595,
|
| 766 |
+
"grad_norm": 2.84375,
|
| 767 |
+
"learning_rate": 1.9044273635774707e-05,
|
| 768 |
+
"loss": 0.6032,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.25396825396825395,
|
| 773 |
+
"grad_norm": 2.75,
|
| 774 |
+
"learning_rate": 1.900386786217083e-05,
|
| 775 |
+
"loss": 0.594,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.2565597667638484,
|
| 780 |
+
"grad_norm": 2.8125,
|
| 781 |
+
"learning_rate": 1.8962670251074276e-05,
|
| 782 |
+
"loss": 0.5958,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.25915127955944284,
|
| 787 |
+
"grad_norm": 2.65625,
|
| 788 |
+
"learning_rate": 1.8920684425573865e-05,
|
| 789 |
+
"loss": 0.5821,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.25915127955944284,
|
| 794 |
+
"eval_loss": 0.5988509058952332,
|
| 795 |
+
"eval_model_preparation_time": 0.0003,
|
| 796 |
+
"eval_runtime": 24.4884,
|
| 797 |
+
"eval_samples_per_second": 106.295,
|
| 798 |
+
"eval_steps_per_second": 13.312,
|
| 799 |
+
"step": 100
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.2617427923550373,
|
| 803 |
+
"grad_norm": 2.65625,
|
| 804 |
+
"learning_rate": 1.887791407807728e-05,
|
| 805 |
+
"loss": 0.5904,
|
| 806 |
+
"step": 101
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.26433430515063167,
|
| 810 |
+
"grad_norm": 2.359375,
|
| 811 |
+
"learning_rate": 1.883436296998631e-05,
|
| 812 |
+
"loss": 0.5913,
|
| 813 |
+
"step": 102
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.2669258179462261,
|
| 817 |
+
"grad_norm": 2.46875,
|
| 818 |
+
"learning_rate": 1.8790034931366073e-05,
|
| 819 |
+
"loss": 0.6114,
|
| 820 |
+
"step": 103
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.26951733074182055,
|
| 824 |
+
"grad_norm": 2.359375,
|
| 825 |
+
"learning_rate": 1.8744933860608183e-05,
|
| 826 |
+
"loss": 0.5803,
|
| 827 |
+
"step": 104
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.272108843537415,
|
| 831 |
+
"grad_norm": 3.40625,
|
| 832 |
+
"learning_rate": 1.8699063724087905e-05,
|
| 833 |
+
"loss": 0.5865,
|
| 834 |
+
"step": 105
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.2747003563330094,
|
| 838 |
+
"grad_norm": 2.28125,
|
| 839 |
+
"learning_rate": 1.865242855581534e-05,
|
| 840 |
+
"loss": 0.586,
|
| 841 |
+
"step": 106
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.2772918691286038,
|
| 845 |
+
"grad_norm": 2.453125,
|
| 846 |
+
"learning_rate": 1.8605032457080655e-05,
|
| 847 |
+
"loss": 0.5926,
|
| 848 |
+
"step": 107
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.27988338192419826,
|
| 852 |
+
"grad_norm": 2.203125,
|
| 853 |
+
"learning_rate": 1.8556879596093393e-05,
|
| 854 |
+
"loss": 0.5927,
|
| 855 |
+
"step": 108
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.2824748947197927,
|
| 859 |
+
"grad_norm": 2.890625,
|
| 860 |
+
"learning_rate": 1.850797420761592e-05,
|
| 861 |
+
"loss": 0.5937,
|
| 862 |
+
"step": 109
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.2850664075153871,
|
| 866 |
+
"grad_norm": 2.390625,
|
| 867 |
+
"learning_rate": 1.8458320592590976e-05,
|
| 868 |
+
"loss": 0.5644,
|
| 869 |
+
"step": 110
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.2850664075153871,
|
| 873 |
+
"eval_loss": 0.5878391265869141,
|
| 874 |
+
"eval_model_preparation_time": 0.0003,
|
| 875 |
+
"eval_runtime": 24.539,
|
| 876 |
+
"eval_samples_per_second": 106.076,
|
| 877 |
+
"eval_steps_per_second": 13.285,
|
| 878 |
+
"step": 110
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.28765792031098153,
|
| 882 |
+
"grad_norm": 2.75,
|
| 883 |
+
"learning_rate": 1.840792311776346e-05,
|
| 884 |
+
"loss": 0.5783,
|
| 885 |
+
"step": 111
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.29024943310657597,
|
| 889 |
+
"grad_norm": 2.375,
|
| 890 |
+
"learning_rate": 1.8356786215296387e-05,
|
| 891 |
+
"loss": 0.5813,
|
| 892 |
+
"step": 112
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.2928409459021704,
|
| 896 |
+
"grad_norm": 2.46875,
|
| 897 |
+
"learning_rate": 1.83049143823811e-05,
|
| 898 |
+
"loss": 0.5788,
|
| 899 |
+
"step": 113
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.2954324586977648,
|
| 903 |
+
"grad_norm": 2.71875,
|
| 904 |
+
"learning_rate": 1.825231218084178e-05,
|
| 905 |
+
"loss": 0.5831,
|
| 906 |
+
"step": 114
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.29802397149335924,
|
| 910 |
+
"grad_norm": 2.484375,
|
| 911 |
+
"learning_rate": 1.8198984236734246e-05,
|
| 912 |
+
"loss": 0.5715,
|
| 913 |
+
"step": 115
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.3006154842889537,
|
| 917 |
+
"grad_norm": 2.546875,
|
| 918 |
+
"learning_rate": 1.8144935239939147e-05,
|
| 919 |
+
"loss": 0.5938,
|
| 920 |
+
"step": 116
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.3032069970845481,
|
| 924 |
+
"grad_norm": 2.90625,
|
| 925 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 926 |
+
"loss": 0.5911,
|
| 927 |
+
"step": 117
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.3057985098801425,
|
| 931 |
+
"grad_norm": 2.859375,
|
| 932 |
+
"learning_rate": 1.8034693164452578e-05,
|
| 933 |
+
"loss": 0.5815,
|
| 934 |
+
"step": 118
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.30839002267573695,
|
| 938 |
+
"grad_norm": 2.65625,
|
| 939 |
+
"learning_rate": 1.7978509780906578e-05,
|
| 940 |
+
"loss": 0.5804,
|
| 941 |
+
"step": 119
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.3109815354713314,
|
| 945 |
+
"grad_norm": 2.828125,
|
| 946 |
+
"learning_rate": 1.7921624734111292e-05,
|
| 947 |
+
"loss": 0.5749,
|
| 948 |
+
"step": 120
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.3109815354713314,
|
| 952 |
+
"eval_loss": 0.5794549584388733,
|
| 953 |
+
"eval_model_preparation_time": 0.0003,
|
| 954 |
+
"eval_runtime": 24.5897,
|
| 955 |
+
"eval_samples_per_second": 105.857,
|
| 956 |
+
"eval_steps_per_second": 13.258,
|
| 957 |
+
"step": 120
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.31357304826692584,
|
| 961 |
+
"grad_norm": 2.703125,
|
| 962 |
+
"learning_rate": 1.786404302677374e-05,
|
| 963 |
+
"loss": 0.5873,
|
| 964 |
+
"step": 121
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.3161645610625202,
|
| 968 |
+
"grad_norm": 2.375,
|
| 969 |
+
"learning_rate": 1.7805769722868132e-05,
|
| 970 |
+
"loss": 0.5856,
|
| 971 |
+
"step": 122
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.31875607385811466,
|
| 975 |
+
"grad_norm": 2.984375,
|
| 976 |
+
"learning_rate": 1.7746809947190567e-05,
|
| 977 |
+
"loss": 0.578,
|
| 978 |
+
"step": 123
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.3213475866537091,
|
| 982 |
+
"grad_norm": 3.421875,
|
| 983 |
+
"learning_rate": 1.768716888490832e-05,
|
| 984 |
+
"loss": 0.5566,
|
| 985 |
+
"step": 124
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.32393909944930355,
|
| 989 |
+
"grad_norm": 2.5625,
|
| 990 |
+
"learning_rate": 1.762685178110382e-05,
|
| 991 |
+
"loss": 0.5638,
|
| 992 |
+
"step": 125
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.32653061224489793,
|
| 996 |
+
"grad_norm": 3.125,
|
| 997 |
+
"learning_rate": 1.7565863940313416e-05,
|
| 998 |
+
"loss": 0.5827,
|
| 999 |
+
"step": 126
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.3291221250404924,
|
| 1003 |
+
"grad_norm": 3.1875,
|
| 1004 |
+
"learning_rate": 1.7504210726060828e-05,
|
| 1005 |
+
"loss": 0.5596,
|
| 1006 |
+
"step": 127
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.3317136378360868,
|
| 1010 |
+
"grad_norm": 2.984375,
|
| 1011 |
+
"learning_rate": 1.7441897560385493e-05,
|
| 1012 |
+
"loss": 0.5768,
|
| 1013 |
+
"step": 128
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.33430515063168126,
|
| 1017 |
+
"grad_norm": 2.546875,
|
| 1018 |
+
"learning_rate": 1.7378929923365706e-05,
|
| 1019 |
+
"loss": 0.5732,
|
| 1020 |
+
"step": 129
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.3368966634272757,
|
| 1024 |
+
"grad_norm": 2.78125,
|
| 1025 |
+
"learning_rate": 1.731531335263669e-05,
|
| 1026 |
+
"loss": 0.5781,
|
| 1027 |
+
"step": 130
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.3368966634272757,
|
| 1031 |
+
"eval_loss": 0.572753369808197,
|
| 1032 |
+
"eval_model_preparation_time": 0.0003,
|
| 1033 |
+
"eval_runtime": 24.5459,
|
| 1034 |
+
"eval_samples_per_second": 106.046,
|
| 1035 |
+
"eval_steps_per_second": 13.281,
|
| 1036 |
+
"step": 130
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.3394881762228701,
|
| 1040 |
+
"grad_norm": 2.421875,
|
| 1041 |
+
"learning_rate": 1.7251053442903597e-05,
|
| 1042 |
+
"loss": 0.5689,
|
| 1043 |
+
"step": 131
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.34207968901846453,
|
| 1047 |
+
"grad_norm": 3.546875,
|
| 1048 |
+
"learning_rate": 1.7186155845449465e-05,
|
| 1049 |
+
"loss": 0.5695,
|
| 1050 |
+
"step": 132
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.34467120181405897,
|
| 1054 |
+
"grad_norm": 2.4375,
|
| 1055 |
+
"learning_rate": 1.712062626763825e-05,
|
| 1056 |
+
"loss": 0.5627,
|
| 1057 |
+
"step": 133
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.3472627146096534,
|
| 1061 |
+
"grad_norm": 2.796875,
|
| 1062 |
+
"learning_rate": 1.7054470472412876e-05,
|
| 1063 |
+
"loss": 0.5759,
|
| 1064 |
+
"step": 134
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.3498542274052478,
|
| 1068 |
+
"grad_norm": 2.4375,
|
| 1069 |
+
"learning_rate": 1.698769427778842e-05,
|
| 1070 |
+
"loss": 0.5662,
|
| 1071 |
+
"step": 135
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.35244574020084224,
|
| 1075 |
+
"grad_norm": 2.40625,
|
| 1076 |
+
"learning_rate": 1.6920303556340462e-05,
|
| 1077 |
+
"loss": 0.5671,
|
| 1078 |
+
"step": 136
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.3550372529964367,
|
| 1082 |
+
"grad_norm": 2.890625,
|
| 1083 |
+
"learning_rate": 1.6852304234688627e-05,
|
| 1084 |
+
"loss": 0.5572,
|
| 1085 |
+
"step": 137
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.3576287657920311,
|
| 1089 |
+
"grad_norm": 2.890625,
|
| 1090 |
+
"learning_rate": 1.678370229297535e-05,
|
| 1091 |
+
"loss": 0.5796,
|
| 1092 |
+
"step": 138
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.3602202785876255,
|
| 1096 |
+
"grad_norm": 3.03125,
|
| 1097 |
+
"learning_rate": 1.6714503764339986e-05,
|
| 1098 |
+
"loss": 0.5642,
|
| 1099 |
+
"step": 139
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.36281179138321995,
|
| 1103 |
+
"grad_norm": 2.3125,
|
| 1104 |
+
"learning_rate": 1.664471473438822e-05,
|
| 1105 |
+
"loss": 0.5711,
|
| 1106 |
+
"step": 140
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.36281179138321995,
|
| 1110 |
+
"eval_loss": 0.566669762134552,
|
| 1111 |
+
"eval_model_preparation_time": 0.0003,
|
| 1112 |
+
"eval_runtime": 24.5724,
|
| 1113 |
+
"eval_samples_per_second": 105.932,
|
| 1114 |
+
"eval_steps_per_second": 13.267,
|
| 1115 |
+
"step": 140
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3654033041788144,
|
| 1119 |
+
"grad_norm": 2.625,
|
| 1120 |
+
"learning_rate": 1.657434134065686e-05,
|
| 1121 |
+
"loss": 0.5559,
|
| 1122 |
+
"step": 141
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.36799481697440883,
|
| 1126 |
+
"grad_norm": 3.015625,
|
| 1127 |
+
"learning_rate": 1.6503389772074104e-05,
|
| 1128 |
+
"loss": 0.575,
|
| 1129 |
+
"step": 142
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.3705863297700032,
|
| 1133 |
+
"grad_norm": 2.984375,
|
| 1134 |
+
"learning_rate": 1.643186626841524e-05,
|
| 1135 |
+
"loss": 0.5851,
|
| 1136 |
+
"step": 143
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.37317784256559766,
|
| 1140 |
+
"grad_norm": 2.609375,
|
| 1141 |
+
"learning_rate": 1.6359777119753887e-05,
|
| 1142 |
+
"loss": 0.559,
|
| 1143 |
+
"step": 144
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.3757693553611921,
|
| 1147 |
+
"grad_norm": 2.40625,
|
| 1148 |
+
"learning_rate": 1.628712866590885e-05,
|
| 1149 |
+
"loss": 0.5759,
|
| 1150 |
+
"step": 145
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.37836086815678655,
|
| 1154 |
+
"grad_norm": 2.328125,
|
| 1155 |
+
"learning_rate": 1.6213927295886547e-05,
|
| 1156 |
+
"loss": 0.5579,
|
| 1157 |
+
"step": 146
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.38095238095238093,
|
| 1161 |
+
"grad_norm": 2.453125,
|
| 1162 |
+
"learning_rate": 1.6140179447319134e-05,
|
| 1163 |
+
"loss": 0.5717,
|
| 1164 |
+
"step": 147
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.3835438937479754,
|
| 1168 |
+
"grad_norm": 2.4375,
|
| 1169 |
+
"learning_rate": 1.6065891605898358e-05,
|
| 1170 |
+
"loss": 0.5531,
|
| 1171 |
+
"step": 148
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.3861354065435698,
|
| 1175 |
+
"grad_norm": 2.484375,
|
| 1176 |
+
"learning_rate": 1.5991070304805184e-05,
|
| 1177 |
+
"loss": 0.5358,
|
| 1178 |
+
"step": 149
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.38872691933916426,
|
| 1182 |
+
"grad_norm": 2.46875,
|
| 1183 |
+
"learning_rate": 1.5915722124135227e-05,
|
| 1184 |
+
"loss": 0.5715,
|
| 1185 |
+
"step": 150
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.38872691933916426,
|
| 1189 |
+
"eval_loss": 0.5618191361427307,
|
| 1190 |
+
"eval_model_preparation_time": 0.0003,
|
| 1191 |
+
"eval_runtime": 24.5943,
|
| 1192 |
+
"eval_samples_per_second": 105.838,
|
| 1193 |
+
"eval_steps_per_second": 13.255,
|
| 1194 |
+
"step": 150
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.39131843213475864,
|
| 1198 |
+
"grad_norm": 2.390625,
|
| 1199 |
+
"learning_rate": 1.5839853690320074e-05,
|
| 1200 |
+
"loss": 0.5413,
|
| 1201 |
+
"step": 151
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.3939099449303531,
|
| 1205 |
+
"grad_norm": 2.28125,
|
| 1206 |
+
"learning_rate": 1.5763471675544547e-05,
|
| 1207 |
+
"loss": 0.5652,
|
| 1208 |
+
"step": 152
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.3965014577259475,
|
| 1212 |
+
"grad_norm": 2.609375,
|
| 1213 |
+
"learning_rate": 1.5686582797159892e-05,
|
| 1214 |
+
"loss": 0.5682,
|
| 1215 |
+
"step": 153
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.39909297052154197,
|
| 1219 |
+
"grad_norm": 2.71875,
|
| 1220 |
+
"learning_rate": 1.5609193817093057e-05,
|
| 1221 |
+
"loss": 0.5577,
|
| 1222 |
+
"step": 154
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.40168448331713635,
|
| 1226 |
+
"grad_norm": 2.65625,
|
| 1227 |
+
"learning_rate": 1.5531311541251995e-05,
|
| 1228 |
+
"loss": 0.5412,
|
| 1229 |
+
"step": 155
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.4042759961127308,
|
| 1233 |
+
"grad_norm": 2.4375,
|
| 1234 |
+
"learning_rate": 1.5452942818927144e-05,
|
| 1235 |
+
"loss": 0.5441,
|
| 1236 |
+
"step": 156
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.40686750890832524,
|
| 1240 |
+
"grad_norm": 2.390625,
|
| 1241 |
+
"learning_rate": 1.5374094542189055e-05,
|
| 1242 |
+
"loss": 0.5764,
|
| 1243 |
+
"step": 157
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.4094590217039197,
|
| 1247 |
+
"grad_norm": 3.078125,
|
| 1248 |
+
"learning_rate": 1.52947736452823e-05,
|
| 1249 |
+
"loss": 0.5763,
|
| 1250 |
+
"step": 158
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.41205053449951407,
|
| 1254 |
+
"grad_norm": 2.5625,
|
| 1255 |
+
"learning_rate": 1.521498710401561e-05,
|
| 1256 |
+
"loss": 0.5482,
|
| 1257 |
+
"step": 159
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.4146420472951085,
|
| 1261 |
+
"grad_norm": 2.375,
|
| 1262 |
+
"learning_rate": 1.513474193514842e-05,
|
| 1263 |
+
"loss": 0.559,
|
| 1264 |
+
"step": 160
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.4146420472951085,
|
| 1268 |
+
"eval_loss": 0.5573883056640625,
|
| 1269 |
+
"eval_model_preparation_time": 0.0003,
|
| 1270 |
+
"eval_runtime": 24.5874,
|
| 1271 |
+
"eval_samples_per_second": 105.867,
|
| 1272 |
+
"eval_steps_per_second": 13.259,
|
| 1273 |
+
"step": 160
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.41723356009070295,
|
| 1277 |
+
"grad_norm": 2.28125,
|
| 1278 |
+
"learning_rate": 1.505404519577379e-05,
|
| 1279 |
+
"loss": 0.5642,
|
| 1280 |
+
"step": 161
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.4198250728862974,
|
| 1284 |
+
"grad_norm": 2.40625,
|
| 1285 |
+
"learning_rate": 1.4972903982697744e-05,
|
| 1286 |
+
"loss": 0.5535,
|
| 1287 |
+
"step": 162
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.42241658568189183,
|
| 1291 |
+
"grad_norm": 2.34375,
|
| 1292 |
+
"learning_rate": 1.4891325431815182e-05,
|
| 1293 |
+
"loss": 0.5519,
|
| 1294 |
+
"step": 163
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.4250080984774862,
|
| 1298 |
+
"grad_norm": 2.0,
|
| 1299 |
+
"learning_rate": 1.48093167174823e-05,
|
| 1300 |
+
"loss": 0.5611,
|
| 1301 |
+
"step": 164
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.42759961127308066,
|
| 1305 |
+
"grad_norm": 2.140625,
|
| 1306 |
+
"learning_rate": 1.4726885051885654e-05,
|
| 1307 |
+
"loss": 0.5556,
|
| 1308 |
+
"step": 165
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.4301911240686751,
|
| 1312 |
+
"grad_norm": 2.40625,
|
| 1313 |
+
"learning_rate": 1.4644037684407883e-05,
|
| 1314 |
+
"loss": 0.5289,
|
| 1315 |
+
"step": 166
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.43278263686426954,
|
| 1319 |
+
"grad_norm": 2.09375,
|
| 1320 |
+
"learning_rate": 1.4560781900990187e-05,
|
| 1321 |
+
"loss": 0.5538,
|
| 1322 |
+
"step": 167
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.43537414965986393,
|
| 1326 |
+
"grad_norm": 2.34375,
|
| 1327 |
+
"learning_rate": 1.4477125023491536e-05,
|
| 1328 |
+
"loss": 0.5589,
|
| 1329 |
+
"step": 168
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.43796566245545837,
|
| 1333 |
+
"grad_norm": 2.359375,
|
| 1334 |
+
"learning_rate": 1.4393074409044802e-05,
|
| 1335 |
+
"loss": 0.5423,
|
| 1336 |
+
"step": 169
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.4405571752510528,
|
| 1340 |
+
"grad_norm": 2.15625,
|
| 1341 |
+
"learning_rate": 1.4308637449409705e-05,
|
| 1342 |
+
"loss": 0.5593,
|
| 1343 |
+
"step": 170
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.4405571752510528,
|
| 1347 |
+
"eval_loss": 0.553532063961029,
|
| 1348 |
+
"eval_model_preparation_time": 0.0003,
|
| 1349 |
+
"eval_runtime": 24.5188,
|
| 1350 |
+
"eval_samples_per_second": 106.163,
|
| 1351 |
+
"eval_steps_per_second": 13.296,
|
| 1352 |
+
"step": 170
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.44314868804664725,
|
| 1356 |
+
"grad_norm": 2.421875,
|
| 1357 |
+
"learning_rate": 1.4223821570322762e-05,
|
| 1358 |
+
"loss": 0.5789,
|
| 1359 |
+
"step": 171
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.44574020084224164,
|
| 1363 |
+
"grad_norm": 2.4375,
|
| 1364 |
+
"learning_rate": 1.4138634230844242e-05,
|
| 1365 |
+
"loss": 0.5693,
|
| 1366 |
+
"step": 172
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.4483317136378361,
|
| 1370 |
+
"grad_norm": 2.296875,
|
| 1371 |
+
"learning_rate": 1.4053082922702183e-05,
|
| 1372 |
+
"loss": 0.5496,
|
| 1373 |
+
"step": 173
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.4509232264334305,
|
| 1377 |
+
"grad_norm": 2.21875,
|
| 1378 |
+
"learning_rate": 1.3967175169633537e-05,
|
| 1379 |
+
"loss": 0.5362,
|
| 1380 |
+
"step": 174
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.45351473922902497,
|
| 1384 |
+
"grad_norm": 2.1875,
|
| 1385 |
+
"learning_rate": 1.3880918526722497e-05,
|
| 1386 |
+
"loss": 0.5739,
|
| 1387 |
+
"step": 175
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.45610625202461935,
|
| 1391 |
+
"grad_norm": 2.421875,
|
| 1392 |
+
"learning_rate": 1.3794320579736084e-05,
|
| 1393 |
+
"loss": 0.5493,
|
| 1394 |
+
"step": 176
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.4586977648202138,
|
| 1398 |
+
"grad_norm": 2.59375,
|
| 1399 |
+
"learning_rate": 1.3707388944457007e-05,
|
| 1400 |
+
"loss": 0.5665,
|
| 1401 |
+
"step": 177
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.46128927761580824,
|
| 1405 |
+
"grad_norm": 2.125,
|
| 1406 |
+
"learning_rate": 1.3620131266013912e-05,
|
| 1407 |
+
"loss": 0.5557,
|
| 1408 |
+
"step": 178
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.4638807904114027,
|
| 1412 |
+
"grad_norm": 2.34375,
|
| 1413 |
+
"learning_rate": 1.3532555218209037e-05,
|
| 1414 |
+
"loss": 0.5402,
|
| 1415 |
+
"step": 179
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.46647230320699706,
|
| 1419 |
+
"grad_norm": 2.375,
|
| 1420 |
+
"learning_rate": 1.344466850284333e-05,
|
| 1421 |
+
"loss": 0.5625,
|
| 1422 |
+
"step": 180
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.46647230320699706,
|
| 1426 |
+
"eval_loss": 0.5502737164497375,
|
| 1427 |
+
"eval_model_preparation_time": 0.0003,
|
| 1428 |
+
"eval_runtime": 24.6233,
|
| 1429 |
+
"eval_samples_per_second": 105.713,
|
| 1430 |
+
"eval_steps_per_second": 13.239,
|
| 1431 |
+
"step": 180
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.4690638160025915,
|
| 1435 |
+
"grad_norm": 2.34375,
|
| 1436 |
+
"learning_rate": 1.335647884903915e-05,
|
| 1437 |
+
"loss": 0.5492,
|
| 1438 |
+
"step": 181
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.47165532879818595,
|
| 1442 |
+
"grad_norm": 2.390625,
|
| 1443 |
+
"learning_rate": 1.3267994012560505e-05,
|
| 1444 |
+
"loss": 0.5493,
|
| 1445 |
+
"step": 182
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.4742468415937804,
|
| 1449 |
+
"grad_norm": 2.453125,
|
| 1450 |
+
"learning_rate": 1.3179221775131005e-05,
|
| 1451 |
+
"loss": 0.5508,
|
| 1452 |
+
"step": 183
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.4768383543893748,
|
| 1456 |
+
"grad_norm": 3.34375,
|
| 1457 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 1458 |
+
"loss": 0.5427,
|
| 1459 |
+
"step": 184
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.4794298671849692,
|
| 1463 |
+
"grad_norm": 2.078125,
|
| 1464 |
+
"learning_rate": 1.300084635000341e-05,
|
| 1465 |
+
"loss": 0.568,
|
| 1466 |
+
"step": 185
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.48202137998056366,
|
| 1470 |
+
"grad_norm": 2.15625,
|
| 1471 |
+
"learning_rate": 1.2911258849380199e-05,
|
| 1472 |
+
"loss": 0.5478,
|
| 1473 |
+
"step": 186
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.4846128927761581,
|
| 1477 |
+
"grad_norm": 2.15625,
|
| 1478 |
+
"learning_rate": 1.2821415320576309e-05,
|
| 1479 |
+
"loss": 0.5582,
|
| 1480 |
+
"step": 187
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.4872044055717525,
|
| 1484 |
+
"grad_norm": 3.0,
|
| 1485 |
+
"learning_rate": 1.273132366480438e-05,
|
| 1486 |
+
"loss": 0.5368,
|
| 1487 |
+
"step": 188
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.4897959183673469,
|
| 1491 |
+
"grad_norm": 2.71875,
|
| 1492 |
+
"learning_rate": 1.2640991805098369e-05,
|
| 1493 |
+
"loss": 0.5608,
|
| 1494 |
+
"step": 189
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.49238743116294137,
|
| 1498 |
+
"grad_norm": 2.203125,
|
| 1499 |
+
"learning_rate": 1.2550427685616767e-05,
|
| 1500 |
+
"loss": 0.5482,
|
| 1501 |
+
"step": 190
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.49238743116294137,
|
| 1505 |
+
"eval_loss": 0.547302782535553,
|
| 1506 |
+
"eval_model_preparation_time": 0.0003,
|
| 1507 |
+
"eval_runtime": 24.5429,
|
| 1508 |
+
"eval_samples_per_second": 106.059,
|
| 1509 |
+
"eval_steps_per_second": 13.283,
|
| 1510 |
+
"step": 190
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.4949789439585358,
|
| 1514 |
+
"grad_norm": 2.640625,
|
| 1515 |
+
"learning_rate": 1.2459639270943944e-05,
|
| 1516 |
+
"loss": 0.5508,
|
| 1517 |
+
"step": 191
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.4975704567541302,
|
| 1521 |
+
"grad_norm": 2.65625,
|
| 1522 |
+
"learning_rate": 1.2368634545389732e-05,
|
| 1523 |
+
"loss": 0.5402,
|
| 1524 |
+
"step": 192
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.5001619695497247,
|
| 1528 |
+
"grad_norm": 2.25,
|
| 1529 |
+
"learning_rate": 1.2277421512287227e-05,
|
| 1530 |
+
"loss": 0.5313,
|
| 1531 |
+
"step": 193
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.502753482345319,
|
| 1535 |
+
"grad_norm": 2.296875,
|
| 1536 |
+
"learning_rate": 1.2186008193288963e-05,
|
| 1537 |
+
"loss": 0.5535,
|
| 1538 |
+
"step": 194
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.5053449951409135,
|
| 1542 |
+
"grad_norm": 2.234375,
|
| 1543 |
+
"learning_rate": 1.2094402627661447e-05,
|
| 1544 |
+
"loss": 0.5375,
|
| 1545 |
+
"step": 195
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.5079365079365079,
|
| 1549 |
+
"grad_norm": 2.375,
|
| 1550 |
+
"learning_rate": 1.2002612871578143e-05,
|
| 1551 |
+
"loss": 0.5564,
|
| 1552 |
+
"step": 196
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.5105280207321024,
|
| 1556 |
+
"grad_norm": 2.5,
|
| 1557 |
+
"learning_rate": 1.1910646997411002e-05,
|
| 1558 |
+
"loss": 0.5459,
|
| 1559 |
+
"step": 197
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.5131195335276968,
|
| 1563 |
+
"grad_norm": 2.3125,
|
| 1564 |
+
"learning_rate": 1.1818513093020514e-05,
|
| 1565 |
+
"loss": 0.5545,
|
| 1566 |
+
"step": 198
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.5157110463232912,
|
| 1570 |
+
"grad_norm": 2.21875,
|
| 1571 |
+
"learning_rate": 1.172621926104446e-05,
|
| 1572 |
+
"loss": 0.535,
|
| 1573 |
+
"step": 199
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.5183025591188857,
|
| 1577 |
+
"grad_norm": 2.234375,
|
| 1578 |
+
"learning_rate": 1.1633773618185302e-05,
|
| 1579 |
+
"loss": 0.5469,
|
| 1580 |
+
"step": 200
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.5183025591188857,
|
| 1584 |
+
"eval_loss": 0.545219898223877,
|
| 1585 |
+
"eval_model_preparation_time": 0.0003,
|
| 1586 |
+
"eval_runtime": 24.4828,
|
| 1587 |
+
"eval_samples_per_second": 106.319,
|
| 1588 |
+
"eval_steps_per_second": 13.315,
|
| 1589 |
+
"step": 200
|
| 1590 |
+
}
|
| 1591 |
+
],
|
| 1592 |
+
"logging_steps": 1,
|
| 1593 |
+
"max_steps": 385,
|
| 1594 |
+
"num_input_tokens_seen": 0,
|
| 1595 |
+
"num_train_epochs": 1,
|
| 1596 |
+
"save_steps": 100,
|
| 1597 |
+
"stateful_callbacks": {
|
| 1598 |
+
"TrainerControl": {
|
| 1599 |
+
"args": {
|
| 1600 |
+
"should_epoch_stop": false,
|
| 1601 |
+
"should_evaluate": false,
|
| 1602 |
+
"should_log": false,
|
| 1603 |
+
"should_save": true,
|
| 1604 |
+
"should_training_stop": false
|
| 1605 |
+
},
|
| 1606 |
+
"attributes": {}
|
| 1607 |
+
}
|
| 1608 |
+
},
|
| 1609 |
+
"total_flos": 5.5651501867008e+16,
|
| 1610 |
+
"train_batch_size": 8,
|
| 1611 |
+
"trial_name": null,
|
| 1612 |
+
"trial_params": null
|
| 1613 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca15ebb16a59dc055f8ae01b1eb1038e869a6556aa3b7b802c58f2dde6a2993c
|
| 3 |
+
size 5304
|
checkpoint-300/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322b2d3fc9de58487c02f1cd651d484d73244f9704de3d5feea36d002a38af0f
|
| 3 |
+
size 748
|
checkpoint-300/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82bdd024a0ba026e4001e0433d3922a27b1242913db7be87e2851d17165b99c8
|
| 3 |
+
size 111
|
checkpoint-300/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aae1e28989d1966e9e8754c3ef09adf98bdd0c3d7d3b8a358a71dc2aebb7105
|
| 3 |
+
size 810702192
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16ce8a7a6f6183711a043b0ec65b90fcae17c5eedf8b9d455994abc12e63bb45
|
| 3 |
+
size 1621580026
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:374644995be79c967030295cf4e5929f6a33d3b1197b8855bc39718b44686552
|
| 3 |
+
size 14244
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97150327a5f2cf78296d100e337e3afcfcbdfef6d10b94b6a3604a6a856e0e12
|
| 3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8
|
| 3 |
+
size 473
|
checkpoint-300/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870f4e2baa6b683221fa52004d5d6f40ab8c9d31961617304b78c910c2c3caf2
|
| 3 |
+
size 2114042
|
checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c4f587ac3a67c3964d3e84248f95ffc8e4f0e64d9de677692df39aa35eb2d11
|
| 3 |
+
size 4845
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,2403 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7774538386783285,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0025915127955944283,
|
| 13 |
+
"grad_norm": 12.625,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.7977,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0051830255911888565,
|
| 20 |
+
"grad_norm": 12.0625,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.7787,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.007774538386783284,
|
| 27 |
+
"grad_norm": 13.0,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.8003,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.010366051182377713,
|
| 34 |
+
"grad_norm": 12.5625,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.787,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01295756397797214,
|
| 41 |
+
"grad_norm": 12.25,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.7684,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.015549076773566569,
|
| 48 |
+
"grad_norm": 12.625,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.7544,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.018140589569160998,
|
| 55 |
+
"grad_norm": 12.5,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.7769,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.020732102364755426,
|
| 62 |
+
"grad_norm": 11.4375,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.7161,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.023323615160349854,
|
| 69 |
+
"grad_norm": 11.5,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.7165,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02591512795594428,
|
| 76 |
+
"grad_norm": 12.1875,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.7437,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02591512795594428,
|
| 83 |
+
"eval_loss": 1.7256978750228882,
|
| 84 |
+
"eval_model_preparation_time": 0.0003,
|
| 85 |
+
"eval_runtime": 24.5814,
|
| 86 |
+
"eval_samples_per_second": 105.893,
|
| 87 |
+
"eval_steps_per_second": 13.262,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.02850664075153871,
|
| 92 |
+
"grad_norm": 11.4375,
|
| 93 |
+
"learning_rate": 4.4e-06,
|
| 94 |
+
"loss": 1.7068,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.031098153547133137,
|
| 99 |
+
"grad_norm": 11.75,
|
| 100 |
+
"learning_rate": 4.800000000000001e-06,
|
| 101 |
+
"loss": 1.688,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.03368966634272757,
|
| 106 |
+
"grad_norm": 11.6875,
|
| 107 |
+
"learning_rate": 5.2e-06,
|
| 108 |
+
"loss": 1.6602,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.036281179138321996,
|
| 113 |
+
"grad_norm": 11.5625,
|
| 114 |
+
"learning_rate": 5.600000000000001e-06,
|
| 115 |
+
"loss": 1.6389,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.038872691933916424,
|
| 120 |
+
"grad_norm": 10.75,
|
| 121 |
+
"learning_rate": 6e-06,
|
| 122 |
+
"loss": 1.6228,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.04146420472951085,
|
| 127 |
+
"grad_norm": 10.8125,
|
| 128 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 129 |
+
"loss": 1.5823,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.04405571752510528,
|
| 134 |
+
"grad_norm": 9.5625,
|
| 135 |
+
"learning_rate": 6.800000000000001e-06,
|
| 136 |
+
"loss": 1.5134,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.04664723032069971,
|
| 141 |
+
"grad_norm": 9.125,
|
| 142 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 143 |
+
"loss": 1.4833,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.049238743116294136,
|
| 148 |
+
"grad_norm": 7.375,
|
| 149 |
+
"learning_rate": 7.600000000000001e-06,
|
| 150 |
+
"loss": 1.4966,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.05183025591188856,
|
| 155 |
+
"grad_norm": 7.0,
|
| 156 |
+
"learning_rate": 8.000000000000001e-06,
|
| 157 |
+
"loss": 1.4653,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.05183025591188856,
|
| 162 |
+
"eval_loss": 1.4041186571121216,
|
| 163 |
+
"eval_model_preparation_time": 0.0003,
|
| 164 |
+
"eval_runtime": 24.6226,
|
| 165 |
+
"eval_samples_per_second": 105.716,
|
| 166 |
+
"eval_steps_per_second": 13.24,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.05442176870748299,
|
| 171 |
+
"grad_norm": 6.0625,
|
| 172 |
+
"learning_rate": 8.400000000000001e-06,
|
| 173 |
+
"loss": 1.3844,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.05701328150307742,
|
| 178 |
+
"grad_norm": 5.375,
|
| 179 |
+
"learning_rate": 8.8e-06,
|
| 180 |
+
"loss": 1.3735,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05960479429867185,
|
| 185 |
+
"grad_norm": 5.09375,
|
| 186 |
+
"learning_rate": 9.200000000000002e-06,
|
| 187 |
+
"loss": 1.3281,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.062196307094266275,
|
| 192 |
+
"grad_norm": 5.25,
|
| 193 |
+
"learning_rate": 9.600000000000001e-06,
|
| 194 |
+
"loss": 1.2837,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.06478781988986071,
|
| 199 |
+
"grad_norm": 5.25,
|
| 200 |
+
"learning_rate": 1e-05,
|
| 201 |
+
"loss": 1.2777,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.06737933268545514,
|
| 206 |
+
"grad_norm": 5.03125,
|
| 207 |
+
"learning_rate": 1.04e-05,
|
| 208 |
+
"loss": 1.2465,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.06997084548104957,
|
| 213 |
+
"grad_norm": 5.0625,
|
| 214 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 215 |
+
"loss": 1.2041,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.07256235827664399,
|
| 220 |
+
"grad_norm": 4.9375,
|
| 221 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 222 |
+
"loss": 1.1524,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.07515387107223842,
|
| 227 |
+
"grad_norm": 4.65625,
|
| 228 |
+
"learning_rate": 1.16e-05,
|
| 229 |
+
"loss": 1.1491,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.07774538386783285,
|
| 234 |
+
"grad_norm": 5.125,
|
| 235 |
+
"learning_rate": 1.2e-05,
|
| 236 |
+
"loss": 1.127,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.07774538386783285,
|
| 241 |
+
"eval_loss": 1.105301856994629,
|
| 242 |
+
"eval_model_preparation_time": 0.0003,
|
| 243 |
+
"eval_runtime": 24.5195,
|
| 244 |
+
"eval_samples_per_second": 106.161,
|
| 245 |
+
"eval_steps_per_second": 13.296,
|
| 246 |
+
"step": 30
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.08033689666342728,
|
| 250 |
+
"grad_norm": 5.09375,
|
| 251 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 252 |
+
"loss": 1.0993,
|
| 253 |
+
"step": 31
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.0829284094590217,
|
| 257 |
+
"grad_norm": 4.9375,
|
| 258 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 259 |
+
"loss": 1.0637,
|
| 260 |
+
"step": 32
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.08551992225461613,
|
| 264 |
+
"grad_norm": 4.75,
|
| 265 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 266 |
+
"loss": 1.0447,
|
| 267 |
+
"step": 33
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.08811143505021056,
|
| 271 |
+
"grad_norm": 5.21875,
|
| 272 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 273 |
+
"loss": 1.047,
|
| 274 |
+
"step": 34
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.09070294784580499,
|
| 278 |
+
"grad_norm": 4.9375,
|
| 279 |
+
"learning_rate": 1.4e-05,
|
| 280 |
+
"loss": 0.9841,
|
| 281 |
+
"step": 35
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.09329446064139942,
|
| 285 |
+
"grad_norm": 4.90625,
|
| 286 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 287 |
+
"loss": 0.9735,
|
| 288 |
+
"step": 36
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.09588597343699384,
|
| 292 |
+
"grad_norm": 5.71875,
|
| 293 |
+
"learning_rate": 1.48e-05,
|
| 294 |
+
"loss": 0.9409,
|
| 295 |
+
"step": 37
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.09847748623258827,
|
| 299 |
+
"grad_norm": 5.0625,
|
| 300 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 301 |
+
"loss": 0.9108,
|
| 302 |
+
"step": 38
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.1010689990281827,
|
| 306 |
+
"grad_norm": 4.90625,
|
| 307 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 308 |
+
"loss": 0.9029,
|
| 309 |
+
"step": 39
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.10366051182377713,
|
| 313 |
+
"grad_norm": 5.0625,
|
| 314 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 315 |
+
"loss": 0.8938,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.10366051182377713,
|
| 320 |
+
"eval_loss": 0.8692858815193176,
|
| 321 |
+
"eval_model_preparation_time": 0.0003,
|
| 322 |
+
"eval_runtime": 24.5016,
|
| 323 |
+
"eval_samples_per_second": 106.238,
|
| 324 |
+
"eval_steps_per_second": 13.305,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.10625202461937155,
|
| 329 |
+
"grad_norm": 5.125,
|
| 330 |
+
"learning_rate": 1.64e-05,
|
| 331 |
+
"loss": 0.8501,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.10884353741496598,
|
| 336 |
+
"grad_norm": 4.53125,
|
| 337 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 338 |
+
"loss": 0.8545,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.11143505021056041,
|
| 343 |
+
"grad_norm": 5.1875,
|
| 344 |
+
"learning_rate": 1.72e-05,
|
| 345 |
+
"loss": 0.8169,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.11402656300615484,
|
| 350 |
+
"grad_norm": 4.5,
|
| 351 |
+
"learning_rate": 1.76e-05,
|
| 352 |
+
"loss": 0.8102,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.11661807580174927,
|
| 357 |
+
"grad_norm": 4.3125,
|
| 358 |
+
"learning_rate": 1.8e-05,
|
| 359 |
+
"loss": 0.8093,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.1192095885973437,
|
| 364 |
+
"grad_norm": 4.28125,
|
| 365 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 366 |
+
"loss": 0.7798,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.12180110139293812,
|
| 371 |
+
"grad_norm": 4.09375,
|
| 372 |
+
"learning_rate": 1.88e-05,
|
| 373 |
+
"loss": 0.7761,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.12439261418853255,
|
| 378 |
+
"grad_norm": 4.125,
|
| 379 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 380 |
+
"loss": 0.7647,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.12698412698412698,
|
| 385 |
+
"grad_norm": 3.765625,
|
| 386 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 387 |
+
"loss": 0.7612,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.12957563977972142,
|
| 392 |
+
"grad_norm": 4.0,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.7498,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.12957563977972142,
|
| 399 |
+
"eval_loss": 0.744697093963623,
|
| 400 |
+
"eval_model_preparation_time": 0.0003,
|
| 401 |
+
"eval_runtime": 24.6181,
|
| 402 |
+
"eval_samples_per_second": 105.735,
|
| 403 |
+
"eval_steps_per_second": 13.242,
|
| 404 |
+
"step": 50
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.13216715257531583,
|
| 408 |
+
"grad_norm": 4.5,
|
| 409 |
+
"learning_rate": 1.9999560279257315e-05,
|
| 410 |
+
"loss": 0.7504,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.13475866537091027,
|
| 415 |
+
"grad_norm": 3.796875,
|
| 416 |
+
"learning_rate": 1.999824115570012e-05,
|
| 417 |
+
"loss": 0.7181,
|
| 418 |
+
"step": 52
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.1373501781665047,
|
| 422 |
+
"grad_norm": 3.703125,
|
| 423 |
+
"learning_rate": 1.9996042745337617e-05,
|
| 424 |
+
"loss": 0.7195,
|
| 425 |
+
"step": 53
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.13994169096209913,
|
| 429 |
+
"grad_norm": 3.921875,
|
| 430 |
+
"learning_rate": 1.999296524150713e-05,
|
| 431 |
+
"loss": 0.7232,
|
| 432 |
+
"step": 54
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.14253320375769354,
|
| 436 |
+
"grad_norm": 3.6875,
|
| 437 |
+
"learning_rate": 1.9989008914857115e-05,
|
| 438 |
+
"loss": 0.725,
|
| 439 |
+
"step": 55
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.14512471655328799,
|
| 443 |
+
"grad_norm": 3.734375,
|
| 444 |
+
"learning_rate": 1.9984174113323352e-05,
|
| 445 |
+
"loss": 0.6972,
|
| 446 |
+
"step": 56
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.1477162293488824,
|
| 450 |
+
"grad_norm": 3.5,
|
| 451 |
+
"learning_rate": 1.9978461262098342e-05,
|
| 452 |
+
"loss": 0.6792,
|
| 453 |
+
"step": 57
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.15030774214447684,
|
| 457 |
+
"grad_norm": 4.0625,
|
| 458 |
+
"learning_rate": 1.9971870863593924e-05,
|
| 459 |
+
"loss": 0.7192,
|
| 460 |
+
"step": 58
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.15289925494007126,
|
| 464 |
+
"grad_norm": 3.75,
|
| 465 |
+
"learning_rate": 1.9964403497397086e-05,
|
| 466 |
+
"loss": 0.7107,
|
| 467 |
+
"step": 59
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1554907677356657,
|
| 471 |
+
"grad_norm": 3.953125,
|
| 472 |
+
"learning_rate": 1.9956059820218982e-05,
|
| 473 |
+
"loss": 0.6866,
|
| 474 |
+
"step": 60
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.1554907677356657,
|
| 478 |
+
"eval_loss": 0.6849498152732849,
|
| 479 |
+
"eval_model_preparation_time": 0.0003,
|
| 480 |
+
"eval_runtime": 24.5203,
|
| 481 |
+
"eval_samples_per_second": 106.157,
|
| 482 |
+
"eval_steps_per_second": 13.295,
|
| 483 |
+
"step": 60
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.1580822805312601,
|
| 487 |
+
"grad_norm": 3.953125,
|
| 488 |
+
"learning_rate": 1.9946840565837206e-05,
|
| 489 |
+
"loss": 0.6818,
|
| 490 |
+
"step": 61
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.16067379332685455,
|
| 494 |
+
"grad_norm": 3.546875,
|
| 495 |
+
"learning_rate": 1.9936746545031225e-05,
|
| 496 |
+
"loss": 0.6855,
|
| 497 |
+
"step": 62
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.16326530612244897,
|
| 501 |
+
"grad_norm": 3.359375,
|
| 502 |
+
"learning_rate": 1.9925778645511112e-05,
|
| 503 |
+
"loss": 0.6799,
|
| 504 |
+
"step": 63
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.1658568189180434,
|
| 508 |
+
"grad_norm": 3.828125,
|
| 509 |
+
"learning_rate": 1.991393783183945e-05,
|
| 510 |
+
"loss": 0.6719,
|
| 511 |
+
"step": 64
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.16844833171363785,
|
| 515 |
+
"grad_norm": 3.0,
|
| 516 |
+
"learning_rate": 1.990122514534651e-05,
|
| 517 |
+
"loss": 0.66,
|
| 518 |
+
"step": 65
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.17103984450923226,
|
| 522 |
+
"grad_norm": 2.96875,
|
| 523 |
+
"learning_rate": 1.988764170403869e-05,
|
| 524 |
+
"loss": 0.6718,
|
| 525 |
+
"step": 66
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.1736313573048267,
|
| 529 |
+
"grad_norm": 3.15625,
|
| 530 |
+
"learning_rate": 1.9873188702500163e-05,
|
| 531 |
+
"loss": 0.6661,
|
| 532 |
+
"step": 67
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.17622287010042112,
|
| 536 |
+
"grad_norm": 2.828125,
|
| 537 |
+
"learning_rate": 1.9857867411787847e-05,
|
| 538 |
+
"loss": 0.6523,
|
| 539 |
+
"step": 68
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.17881438289601556,
|
| 543 |
+
"grad_norm": 3.203125,
|
| 544 |
+
"learning_rate": 1.9841679179319605e-05,
|
| 545 |
+
"loss": 0.6494,
|
| 546 |
+
"step": 69
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.18140589569160998,
|
| 550 |
+
"grad_norm": 2.875,
|
| 551 |
+
"learning_rate": 1.982462542875576e-05,
|
| 552 |
+
"loss": 0.6411,
|
| 553 |
+
"step": 70
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.18140589569160998,
|
| 557 |
+
"eval_loss": 0.6511064171791077,
|
| 558 |
+
"eval_model_preparation_time": 0.0003,
|
| 559 |
+
"eval_runtime": 24.5304,
|
| 560 |
+
"eval_samples_per_second": 106.113,
|
| 561 |
+
"eval_steps_per_second": 13.29,
|
| 562 |
+
"step": 70
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.18399740848720442,
|
| 566 |
+
"grad_norm": 3.296875,
|
| 567 |
+
"learning_rate": 1.9806707659873886e-05,
|
| 568 |
+
"loss": 0.6463,
|
| 569 |
+
"step": 71
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.18658892128279883,
|
| 573 |
+
"grad_norm": 3.0625,
|
| 574 |
+
"learning_rate": 1.9787927448436913e-05,
|
| 575 |
+
"loss": 0.6375,
|
| 576 |
+
"step": 72
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.18918043407839327,
|
| 580 |
+
"grad_norm": 2.75,
|
| 581 |
+
"learning_rate": 1.9768286446054533e-05,
|
| 582 |
+
"loss": 0.6386,
|
| 583 |
+
"step": 73
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.1917719468739877,
|
| 587 |
+
"grad_norm": 2.875,
|
| 588 |
+
"learning_rate": 1.974778638003799e-05,
|
| 589 |
+
"loss": 0.6368,
|
| 590 |
+
"step": 74
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.19436345966958213,
|
| 594 |
+
"grad_norm": 2.953125,
|
| 595 |
+
"learning_rate": 1.972642905324813e-05,
|
| 596 |
+
"loss": 0.6271,
|
| 597 |
+
"step": 75
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.19695497246517654,
|
| 601 |
+
"grad_norm": 2.921875,
|
| 602 |
+
"learning_rate": 1.9704216343936875e-05,
|
| 603 |
+
"loss": 0.6501,
|
| 604 |
+
"step": 76
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.19954648526077098,
|
| 608 |
+
"grad_norm": 3.015625,
|
| 609 |
+
"learning_rate": 1.9681150205582025e-05,
|
| 610 |
+
"loss": 0.6111,
|
| 611 |
+
"step": 77
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2021379980563654,
|
| 615 |
+
"grad_norm": 3.171875,
|
| 616 |
+
"learning_rate": 1.9657232666715485e-05,
|
| 617 |
+
"loss": 0.651,
|
| 618 |
+
"step": 78
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.20472951085195984,
|
| 622 |
+
"grad_norm": 3.0625,
|
| 623 |
+
"learning_rate": 1.9632465830744846e-05,
|
| 624 |
+
"loss": 0.6184,
|
| 625 |
+
"step": 79
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.20732102364755425,
|
| 629 |
+
"grad_norm": 3.25,
|
| 630 |
+
"learning_rate": 1.9606851875768404e-05,
|
| 631 |
+
"loss": 0.6259,
|
| 632 |
+
"step": 80
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20732102364755425,
|
| 636 |
+
"eval_loss": 0.6278263330459595,
|
| 637 |
+
"eval_model_preparation_time": 0.0003,
|
| 638 |
+
"eval_runtime": 24.4892,
|
| 639 |
+
"eval_samples_per_second": 106.292,
|
| 640 |
+
"eval_steps_per_second": 13.312,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2099125364431487,
|
| 645 |
+
"grad_norm": 2.875,
|
| 646 |
+
"learning_rate": 1.9580393054383622e-05,
|
| 647 |
+
"loss": 0.6288,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2125040492387431,
|
| 652 |
+
"grad_norm": 3.359375,
|
| 653 |
+
"learning_rate": 1.9553091693489018e-05,
|
| 654 |
+
"loss": 0.6403,
|
| 655 |
+
"step": 82
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.21509556203433755,
|
| 659 |
+
"grad_norm": 2.921875,
|
| 660 |
+
"learning_rate": 1.9524950194079534e-05,
|
| 661 |
+
"loss": 0.621,
|
| 662 |
+
"step": 83
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.21768707482993196,
|
| 666 |
+
"grad_norm": 2.84375,
|
| 667 |
+
"learning_rate": 1.9495971031035367e-05,
|
| 668 |
+
"loss": 0.6135,
|
| 669 |
+
"step": 84
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.2202785876255264,
|
| 673 |
+
"grad_norm": 2.921875,
|
| 674 |
+
"learning_rate": 1.9466156752904344e-05,
|
| 675 |
+
"loss": 0.6211,
|
| 676 |
+
"step": 85
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.22287010042112082,
|
| 680 |
+
"grad_norm": 3.109375,
|
| 681 |
+
"learning_rate": 1.9435509981677764e-05,
|
| 682 |
+
"loss": 0.6198,
|
| 683 |
+
"step": 86
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.22546161321671526,
|
| 687 |
+
"grad_norm": 2.625,
|
| 688 |
+
"learning_rate": 1.9404033412559828e-05,
|
| 689 |
+
"loss": 0.5972,
|
| 690 |
+
"step": 87
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.22805312601230968,
|
| 694 |
+
"grad_norm": 3.0,
|
| 695 |
+
"learning_rate": 1.9371729813730606e-05,
|
| 696 |
+
"loss": 0.614,
|
| 697 |
+
"step": 88
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.23064463880790412,
|
| 701 |
+
"grad_norm": 2.75,
|
| 702 |
+
"learning_rate": 1.9338602026102594e-05,
|
| 703 |
+
"loss": 0.5998,
|
| 704 |
+
"step": 89
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.23323615160349853,
|
| 708 |
+
"grad_norm": 2.796875,
|
| 709 |
+
"learning_rate": 1.9304652963070868e-05,
|
| 710 |
+
"loss": 0.6181,
|
| 711 |
+
"step": 90
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.23323615160349853,
|
| 715 |
+
"eval_loss": 0.6108965277671814,
|
| 716 |
+
"eval_model_preparation_time": 0.0003,
|
| 717 |
+
"eval_runtime": 24.4982,
|
| 718 |
+
"eval_samples_per_second": 106.253,
|
| 719 |
+
"eval_steps_per_second": 13.307,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.23582766439909297,
|
| 724 |
+
"grad_norm": 2.8125,
|
| 725 |
+
"learning_rate": 1.9269885610256866e-05,
|
| 726 |
+
"loss": 0.6059,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2384191771946874,
|
| 731 |
+
"grad_norm": 2.734375,
|
| 732 |
+
"learning_rate": 1.9234303025245835e-05,
|
| 733 |
+
"loss": 0.6165,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.24101068999028183,
|
| 738 |
+
"grad_norm": 2.984375,
|
| 739 |
+
"learning_rate": 1.919790833731791e-05,
|
| 740 |
+
"loss": 0.6241,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.24360220278587624,
|
| 745 |
+
"grad_norm": 3.015625,
|
| 746 |
+
"learning_rate": 1.9160704747172935e-05,
|
| 747 |
+
"loss": 0.5913,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.24619371558147068,
|
| 752 |
+
"grad_norm": 2.84375,
|
| 753 |
+
"learning_rate": 1.9122695526648968e-05,
|
| 754 |
+
"loss": 0.585,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.2487852283770651,
|
| 759 |
+
"grad_norm": 3.484375,
|
| 760 |
+
"learning_rate": 1.9083884018434545e-05,
|
| 761 |
+
"loss": 0.5897,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.2513767411726595,
|
| 766 |
+
"grad_norm": 2.84375,
|
| 767 |
+
"learning_rate": 1.9044273635774707e-05,
|
| 768 |
+
"loss": 0.6032,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.25396825396825395,
|
| 773 |
+
"grad_norm": 2.75,
|
| 774 |
+
"learning_rate": 1.900386786217083e-05,
|
| 775 |
+
"loss": 0.594,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.2565597667638484,
|
| 780 |
+
"grad_norm": 2.8125,
|
| 781 |
+
"learning_rate": 1.8962670251074276e-05,
|
| 782 |
+
"loss": 0.5958,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.25915127955944284,
|
| 787 |
+
"grad_norm": 2.65625,
|
| 788 |
+
"learning_rate": 1.8920684425573865e-05,
|
| 789 |
+
"loss": 0.5821,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.25915127955944284,
|
| 794 |
+
"eval_loss": 0.5988509058952332,
|
| 795 |
+
"eval_model_preparation_time": 0.0003,
|
| 796 |
+
"eval_runtime": 24.4884,
|
| 797 |
+
"eval_samples_per_second": 106.295,
|
| 798 |
+
"eval_steps_per_second": 13.312,
|
| 799 |
+
"step": 100
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.2617427923550373,
|
| 803 |
+
"grad_norm": 2.65625,
|
| 804 |
+
"learning_rate": 1.887791407807728e-05,
|
| 805 |
+
"loss": 0.5904,
|
| 806 |
+
"step": 101
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.26433430515063167,
|
| 810 |
+
"grad_norm": 2.359375,
|
| 811 |
+
"learning_rate": 1.883436296998631e-05,
|
| 812 |
+
"loss": 0.5913,
|
| 813 |
+
"step": 102
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.2669258179462261,
|
| 817 |
+
"grad_norm": 2.46875,
|
| 818 |
+
"learning_rate": 1.8790034931366073e-05,
|
| 819 |
+
"loss": 0.6114,
|
| 820 |
+
"step": 103
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.26951733074182055,
|
| 824 |
+
"grad_norm": 2.359375,
|
| 825 |
+
"learning_rate": 1.8744933860608183e-05,
|
| 826 |
+
"loss": 0.5803,
|
| 827 |
+
"step": 104
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.272108843537415,
|
| 831 |
+
"grad_norm": 3.40625,
|
| 832 |
+
"learning_rate": 1.8699063724087905e-05,
|
| 833 |
+
"loss": 0.5865,
|
| 834 |
+
"step": 105
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.2747003563330094,
|
| 838 |
+
"grad_norm": 2.28125,
|
| 839 |
+
"learning_rate": 1.865242855581534e-05,
|
| 840 |
+
"loss": 0.586,
|
| 841 |
+
"step": 106
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.2772918691286038,
|
| 845 |
+
"grad_norm": 2.453125,
|
| 846 |
+
"learning_rate": 1.8605032457080655e-05,
|
| 847 |
+
"loss": 0.5926,
|
| 848 |
+
"step": 107
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.27988338192419826,
|
| 852 |
+
"grad_norm": 2.203125,
|
| 853 |
+
"learning_rate": 1.8556879596093393e-05,
|
| 854 |
+
"loss": 0.5927,
|
| 855 |
+
"step": 108
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.2824748947197927,
|
| 859 |
+
"grad_norm": 2.890625,
|
| 860 |
+
"learning_rate": 1.850797420761592e-05,
|
| 861 |
+
"loss": 0.5937,
|
| 862 |
+
"step": 109
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.2850664075153871,
|
| 866 |
+
"grad_norm": 2.390625,
|
| 867 |
+
"learning_rate": 1.8458320592590976e-05,
|
| 868 |
+
"loss": 0.5644,
|
| 869 |
+
"step": 110
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.2850664075153871,
|
| 873 |
+
"eval_loss": 0.5878391265869141,
|
| 874 |
+
"eval_model_preparation_time": 0.0003,
|
| 875 |
+
"eval_runtime": 24.539,
|
| 876 |
+
"eval_samples_per_second": 106.076,
|
| 877 |
+
"eval_steps_per_second": 13.285,
|
| 878 |
+
"step": 110
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.28765792031098153,
|
| 882 |
+
"grad_norm": 2.75,
|
| 883 |
+
"learning_rate": 1.840792311776346e-05,
|
| 884 |
+
"loss": 0.5783,
|
| 885 |
+
"step": 111
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.29024943310657597,
|
| 889 |
+
"grad_norm": 2.375,
|
| 890 |
+
"learning_rate": 1.8356786215296387e-05,
|
| 891 |
+
"loss": 0.5813,
|
| 892 |
+
"step": 112
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.2928409459021704,
|
| 896 |
+
"grad_norm": 2.46875,
|
| 897 |
+
"learning_rate": 1.83049143823811e-05,
|
| 898 |
+
"loss": 0.5788,
|
| 899 |
+
"step": 113
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.2954324586977648,
|
| 903 |
+
"grad_norm": 2.71875,
|
| 904 |
+
"learning_rate": 1.825231218084178e-05,
|
| 905 |
+
"loss": 0.5831,
|
| 906 |
+
"step": 114
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.29802397149335924,
|
| 910 |
+
"grad_norm": 2.484375,
|
| 911 |
+
"learning_rate": 1.8198984236734246e-05,
|
| 912 |
+
"loss": 0.5715,
|
| 913 |
+
"step": 115
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.3006154842889537,
|
| 917 |
+
"grad_norm": 2.546875,
|
| 918 |
+
"learning_rate": 1.8144935239939147e-05,
|
| 919 |
+
"loss": 0.5938,
|
| 920 |
+
"step": 116
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.3032069970845481,
|
| 924 |
+
"grad_norm": 2.90625,
|
| 925 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 926 |
+
"loss": 0.5911,
|
| 927 |
+
"step": 117
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.3057985098801425,
|
| 931 |
+
"grad_norm": 2.859375,
|
| 932 |
+
"learning_rate": 1.8034693164452578e-05,
|
| 933 |
+
"loss": 0.5815,
|
| 934 |
+
"step": 118
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.30839002267573695,
|
| 938 |
+
"grad_norm": 2.65625,
|
| 939 |
+
"learning_rate": 1.7978509780906578e-05,
|
| 940 |
+
"loss": 0.5804,
|
| 941 |
+
"step": 119
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.3109815354713314,
|
| 945 |
+
"grad_norm": 2.828125,
|
| 946 |
+
"learning_rate": 1.7921624734111292e-05,
|
| 947 |
+
"loss": 0.5749,
|
| 948 |
+
"step": 120
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.3109815354713314,
|
| 952 |
+
"eval_loss": 0.5794549584388733,
|
| 953 |
+
"eval_model_preparation_time": 0.0003,
|
| 954 |
+
"eval_runtime": 24.5897,
|
| 955 |
+
"eval_samples_per_second": 105.857,
|
| 956 |
+
"eval_steps_per_second": 13.258,
|
| 957 |
+
"step": 120
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.31357304826692584,
|
| 961 |
+
"grad_norm": 2.703125,
|
| 962 |
+
"learning_rate": 1.786404302677374e-05,
|
| 963 |
+
"loss": 0.5873,
|
| 964 |
+
"step": 121
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.3161645610625202,
|
| 968 |
+
"grad_norm": 2.375,
|
| 969 |
+
"learning_rate": 1.7805769722868132e-05,
|
| 970 |
+
"loss": 0.5856,
|
| 971 |
+
"step": 122
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.31875607385811466,
|
| 975 |
+
"grad_norm": 2.984375,
|
| 976 |
+
"learning_rate": 1.7746809947190567e-05,
|
| 977 |
+
"loss": 0.578,
|
| 978 |
+
"step": 123
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.3213475866537091,
|
| 982 |
+
"grad_norm": 3.421875,
|
| 983 |
+
"learning_rate": 1.768716888490832e-05,
|
| 984 |
+
"loss": 0.5566,
|
| 985 |
+
"step": 124
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.32393909944930355,
|
| 989 |
+
"grad_norm": 2.5625,
|
| 990 |
+
"learning_rate": 1.762685178110382e-05,
|
| 991 |
+
"loss": 0.5638,
|
| 992 |
+
"step": 125
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.32653061224489793,
|
| 996 |
+
"grad_norm": 3.125,
|
| 997 |
+
"learning_rate": 1.7565863940313416e-05,
|
| 998 |
+
"loss": 0.5827,
|
| 999 |
+
"step": 126
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.3291221250404924,
|
| 1003 |
+
"grad_norm": 3.1875,
|
| 1004 |
+
"learning_rate": 1.7504210726060828e-05,
|
| 1005 |
+
"loss": 0.5596,
|
| 1006 |
+
"step": 127
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.3317136378360868,
|
| 1010 |
+
"grad_norm": 2.984375,
|
| 1011 |
+
"learning_rate": 1.7441897560385493e-05,
|
| 1012 |
+
"loss": 0.5768,
|
| 1013 |
+
"step": 128
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.33430515063168126,
|
| 1017 |
+
"grad_norm": 2.546875,
|
| 1018 |
+
"learning_rate": 1.7378929923365706e-05,
|
| 1019 |
+
"loss": 0.5732,
|
| 1020 |
+
"step": 129
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.3368966634272757,
|
| 1024 |
+
"grad_norm": 2.78125,
|
| 1025 |
+
"learning_rate": 1.731531335263669e-05,
|
| 1026 |
+
"loss": 0.5781,
|
| 1027 |
+
"step": 130
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.3368966634272757,
|
| 1031 |
+
"eval_loss": 0.572753369808197,
|
| 1032 |
+
"eval_model_preparation_time": 0.0003,
|
| 1033 |
+
"eval_runtime": 24.5459,
|
| 1034 |
+
"eval_samples_per_second": 106.046,
|
| 1035 |
+
"eval_steps_per_second": 13.281,
|
| 1036 |
+
"step": 130
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.3394881762228701,
|
| 1040 |
+
"grad_norm": 2.421875,
|
| 1041 |
+
"learning_rate": 1.7251053442903597e-05,
|
| 1042 |
+
"loss": 0.5689,
|
| 1043 |
+
"step": 131
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.34207968901846453,
|
| 1047 |
+
"grad_norm": 3.546875,
|
| 1048 |
+
"learning_rate": 1.7186155845449465e-05,
|
| 1049 |
+
"loss": 0.5695,
|
| 1050 |
+
"step": 132
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.34467120181405897,
|
| 1054 |
+
"grad_norm": 2.4375,
|
| 1055 |
+
"learning_rate": 1.712062626763825e-05,
|
| 1056 |
+
"loss": 0.5627,
|
| 1057 |
+
"step": 133
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.3472627146096534,
|
| 1061 |
+
"grad_norm": 2.796875,
|
| 1062 |
+
"learning_rate": 1.7054470472412876e-05,
|
| 1063 |
+
"loss": 0.5759,
|
| 1064 |
+
"step": 134
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.3498542274052478,
|
| 1068 |
+
"grad_norm": 2.4375,
|
| 1069 |
+
"learning_rate": 1.698769427778842e-05,
|
| 1070 |
+
"loss": 0.5662,
|
| 1071 |
+
"step": 135
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.35244574020084224,
|
| 1075 |
+
"grad_norm": 2.40625,
|
| 1076 |
+
"learning_rate": 1.6920303556340462e-05,
|
| 1077 |
+
"loss": 0.5671,
|
| 1078 |
+
"step": 136
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.3550372529964367,
|
| 1082 |
+
"grad_norm": 2.890625,
|
| 1083 |
+
"learning_rate": 1.6852304234688627e-05,
|
| 1084 |
+
"loss": 0.5572,
|
| 1085 |
+
"step": 137
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.3576287657920311,
|
| 1089 |
+
"grad_norm": 2.890625,
|
| 1090 |
+
"learning_rate": 1.678370229297535e-05,
|
| 1091 |
+
"loss": 0.5796,
|
| 1092 |
+
"step": 138
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.3602202785876255,
|
| 1096 |
+
"grad_norm": 3.03125,
|
| 1097 |
+
"learning_rate": 1.6714503764339986e-05,
|
| 1098 |
+
"loss": 0.5642,
|
| 1099 |
+
"step": 139
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.36281179138321995,
|
| 1103 |
+
"grad_norm": 2.3125,
|
| 1104 |
+
"learning_rate": 1.664471473438822e-05,
|
| 1105 |
+
"loss": 0.5711,
|
| 1106 |
+
"step": 140
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.36281179138321995,
|
| 1110 |
+
"eval_loss": 0.566669762134552,
|
| 1111 |
+
"eval_model_preparation_time": 0.0003,
|
| 1112 |
+
"eval_runtime": 24.5724,
|
| 1113 |
+
"eval_samples_per_second": 105.932,
|
| 1114 |
+
"eval_steps_per_second": 13.267,
|
| 1115 |
+
"step": 140
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3654033041788144,
|
| 1119 |
+
"grad_norm": 2.625,
|
| 1120 |
+
"learning_rate": 1.657434134065686e-05,
|
| 1121 |
+
"loss": 0.5559,
|
| 1122 |
+
"step": 141
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.36799481697440883,
|
| 1126 |
+
"grad_norm": 3.015625,
|
| 1127 |
+
"learning_rate": 1.6503389772074104e-05,
|
| 1128 |
+
"loss": 0.575,
|
| 1129 |
+
"step": 142
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.3705863297700032,
|
| 1133 |
+
"grad_norm": 2.984375,
|
| 1134 |
+
"learning_rate": 1.643186626841524e-05,
|
| 1135 |
+
"loss": 0.5851,
|
| 1136 |
+
"step": 143
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.37317784256559766,
|
| 1140 |
+
"grad_norm": 2.609375,
|
| 1141 |
+
"learning_rate": 1.6359777119753887e-05,
|
| 1142 |
+
"loss": 0.559,
|
| 1143 |
+
"step": 144
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.3757693553611921,
|
| 1147 |
+
"grad_norm": 2.40625,
|
| 1148 |
+
"learning_rate": 1.628712866590885e-05,
|
| 1149 |
+
"loss": 0.5759,
|
| 1150 |
+
"step": 145
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.37836086815678655,
|
| 1154 |
+
"grad_norm": 2.328125,
|
| 1155 |
+
"learning_rate": 1.6213927295886547e-05,
|
| 1156 |
+
"loss": 0.5579,
|
| 1157 |
+
"step": 146
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.38095238095238093,
|
| 1161 |
+
"grad_norm": 2.453125,
|
| 1162 |
+
"learning_rate": 1.6140179447319134e-05,
|
| 1163 |
+
"loss": 0.5717,
|
| 1164 |
+
"step": 147
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.3835438937479754,
|
| 1168 |
+
"grad_norm": 2.4375,
|
| 1169 |
+
"learning_rate": 1.6065891605898358e-05,
|
| 1170 |
+
"loss": 0.5531,
|
| 1171 |
+
"step": 148
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.3861354065435698,
|
| 1175 |
+
"grad_norm": 2.484375,
|
| 1176 |
+
"learning_rate": 1.5991070304805184e-05,
|
| 1177 |
+
"loss": 0.5358,
|
| 1178 |
+
"step": 149
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.38872691933916426,
|
| 1182 |
+
"grad_norm": 2.46875,
|
| 1183 |
+
"learning_rate": 1.5915722124135227e-05,
|
| 1184 |
+
"loss": 0.5715,
|
| 1185 |
+
"step": 150
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.38872691933916426,
|
| 1189 |
+
"eval_loss": 0.5618191361427307,
|
| 1190 |
+
"eval_model_preparation_time": 0.0003,
|
| 1191 |
+
"eval_runtime": 24.5943,
|
| 1192 |
+
"eval_samples_per_second": 105.838,
|
| 1193 |
+
"eval_steps_per_second": 13.255,
|
| 1194 |
+
"step": 150
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.39131843213475864,
|
| 1198 |
+
"grad_norm": 2.390625,
|
| 1199 |
+
"learning_rate": 1.5839853690320074e-05,
|
| 1200 |
+
"loss": 0.5413,
|
| 1201 |
+
"step": 151
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.3939099449303531,
|
| 1205 |
+
"grad_norm": 2.28125,
|
| 1206 |
+
"learning_rate": 1.5763471675544547e-05,
|
| 1207 |
+
"loss": 0.5652,
|
| 1208 |
+
"step": 152
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.3965014577259475,
|
| 1212 |
+
"grad_norm": 2.609375,
|
| 1213 |
+
"learning_rate": 1.5686582797159892e-05,
|
| 1214 |
+
"loss": 0.5682,
|
| 1215 |
+
"step": 153
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.39909297052154197,
|
| 1219 |
+
"grad_norm": 2.71875,
|
| 1220 |
+
"learning_rate": 1.5609193817093057e-05,
|
| 1221 |
+
"loss": 0.5577,
|
| 1222 |
+
"step": 154
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.40168448331713635,
|
| 1226 |
+
"grad_norm": 2.65625,
|
| 1227 |
+
"learning_rate": 1.5531311541251995e-05,
|
| 1228 |
+
"loss": 0.5412,
|
| 1229 |
+
"step": 155
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.4042759961127308,
|
| 1233 |
+
"grad_norm": 2.4375,
|
| 1234 |
+
"learning_rate": 1.5452942818927144e-05,
|
| 1235 |
+
"loss": 0.5441,
|
| 1236 |
+
"step": 156
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.40686750890832524,
|
| 1240 |
+
"grad_norm": 2.390625,
|
| 1241 |
+
"learning_rate": 1.5374094542189055e-05,
|
| 1242 |
+
"loss": 0.5764,
|
| 1243 |
+
"step": 157
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.4094590217039197,
|
| 1247 |
+
"grad_norm": 3.078125,
|
| 1248 |
+
"learning_rate": 1.52947736452823e-05,
|
| 1249 |
+
"loss": 0.5763,
|
| 1250 |
+
"step": 158
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.41205053449951407,
|
| 1254 |
+
"grad_norm": 2.5625,
|
| 1255 |
+
"learning_rate": 1.521498710401561e-05,
|
| 1256 |
+
"loss": 0.5482,
|
| 1257 |
+
"step": 159
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.4146420472951085,
|
| 1261 |
+
"grad_norm": 2.375,
|
| 1262 |
+
"learning_rate": 1.513474193514842e-05,
|
| 1263 |
+
"loss": 0.559,
|
| 1264 |
+
"step": 160
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.4146420472951085,
|
| 1268 |
+
"eval_loss": 0.5573883056640625,
|
| 1269 |
+
"eval_model_preparation_time": 0.0003,
|
| 1270 |
+
"eval_runtime": 24.5874,
|
| 1271 |
+
"eval_samples_per_second": 105.867,
|
| 1272 |
+
"eval_steps_per_second": 13.259,
|
| 1273 |
+
"step": 160
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.41723356009070295,
|
| 1277 |
+
"grad_norm": 2.28125,
|
| 1278 |
+
"learning_rate": 1.505404519577379e-05,
|
| 1279 |
+
"loss": 0.5642,
|
| 1280 |
+
"step": 161
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.4198250728862974,
|
| 1284 |
+
"grad_norm": 2.40625,
|
| 1285 |
+
"learning_rate": 1.4972903982697744e-05,
|
| 1286 |
+
"loss": 0.5535,
|
| 1287 |
+
"step": 162
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.42241658568189183,
|
| 1291 |
+
"grad_norm": 2.34375,
|
| 1292 |
+
"learning_rate": 1.4891325431815182e-05,
|
| 1293 |
+
"loss": 0.5519,
|
| 1294 |
+
"step": 163
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.4250080984774862,
|
| 1298 |
+
"grad_norm": 2.0,
|
| 1299 |
+
"learning_rate": 1.48093167174823e-05,
|
| 1300 |
+
"loss": 0.5611,
|
| 1301 |
+
"step": 164
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.42759961127308066,
|
| 1305 |
+
"grad_norm": 2.140625,
|
| 1306 |
+
"learning_rate": 1.4726885051885654e-05,
|
| 1307 |
+
"loss": 0.5556,
|
| 1308 |
+
"step": 165
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.4301911240686751,
|
| 1312 |
+
"grad_norm": 2.40625,
|
| 1313 |
+
"learning_rate": 1.4644037684407883e-05,
|
| 1314 |
+
"loss": 0.5289,
|
| 1315 |
+
"step": 166
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.43278263686426954,
|
| 1319 |
+
"grad_norm": 2.09375,
|
| 1320 |
+
"learning_rate": 1.4560781900990187e-05,
|
| 1321 |
+
"loss": 0.5538,
|
| 1322 |
+
"step": 167
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.43537414965986393,
|
| 1326 |
+
"grad_norm": 2.34375,
|
| 1327 |
+
"learning_rate": 1.4477125023491536e-05,
|
| 1328 |
+
"loss": 0.5589,
|
| 1329 |
+
"step": 168
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.43796566245545837,
|
| 1333 |
+
"grad_norm": 2.359375,
|
| 1334 |
+
"learning_rate": 1.4393074409044802e-05,
|
| 1335 |
+
"loss": 0.5423,
|
| 1336 |
+
"step": 169
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.4405571752510528,
|
| 1340 |
+
"grad_norm": 2.15625,
|
| 1341 |
+
"learning_rate": 1.4308637449409705e-05,
|
| 1342 |
+
"loss": 0.5593,
|
| 1343 |
+
"step": 170
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.4405571752510528,
|
| 1347 |
+
"eval_loss": 0.553532063961029,
|
| 1348 |
+
"eval_model_preparation_time": 0.0003,
|
| 1349 |
+
"eval_runtime": 24.5188,
|
| 1350 |
+
"eval_samples_per_second": 106.163,
|
| 1351 |
+
"eval_steps_per_second": 13.296,
|
| 1352 |
+
"step": 170
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.44314868804664725,
|
| 1356 |
+
"grad_norm": 2.421875,
|
| 1357 |
+
"learning_rate": 1.4223821570322762e-05,
|
| 1358 |
+
"loss": 0.5789,
|
| 1359 |
+
"step": 171
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.44574020084224164,
|
| 1363 |
+
"grad_norm": 2.4375,
|
| 1364 |
+
"learning_rate": 1.4138634230844242e-05,
|
| 1365 |
+
"loss": 0.5693,
|
| 1366 |
+
"step": 172
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.4483317136378361,
|
| 1370 |
+
"grad_norm": 2.296875,
|
| 1371 |
+
"learning_rate": 1.4053082922702183e-05,
|
| 1372 |
+
"loss": 0.5496,
|
| 1373 |
+
"step": 173
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.4509232264334305,
|
| 1377 |
+
"grad_norm": 2.21875,
|
| 1378 |
+
"learning_rate": 1.3967175169633537e-05,
|
| 1379 |
+
"loss": 0.5362,
|
| 1380 |
+
"step": 174
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.45351473922902497,
|
| 1384 |
+
"grad_norm": 2.1875,
|
| 1385 |
+
"learning_rate": 1.3880918526722497e-05,
|
| 1386 |
+
"loss": 0.5739,
|
| 1387 |
+
"step": 175
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.45610625202461935,
|
| 1391 |
+
"grad_norm": 2.421875,
|
| 1392 |
+
"learning_rate": 1.3794320579736084e-05,
|
| 1393 |
+
"loss": 0.5493,
|
| 1394 |
+
"step": 176
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.4586977648202138,
|
| 1398 |
+
"grad_norm": 2.59375,
|
| 1399 |
+
"learning_rate": 1.3707388944457007e-05,
|
| 1400 |
+
"loss": 0.5665,
|
| 1401 |
+
"step": 177
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.46128927761580824,
|
| 1405 |
+
"grad_norm": 2.125,
|
| 1406 |
+
"learning_rate": 1.3620131266013912e-05,
|
| 1407 |
+
"loss": 0.5557,
|
| 1408 |
+
"step": 178
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.4638807904114027,
|
| 1412 |
+
"grad_norm": 2.34375,
|
| 1413 |
+
"learning_rate": 1.3532555218209037e-05,
|
| 1414 |
+
"loss": 0.5402,
|
| 1415 |
+
"step": 179
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.46647230320699706,
|
| 1419 |
+
"grad_norm": 2.375,
|
| 1420 |
+
"learning_rate": 1.344466850284333e-05,
|
| 1421 |
+
"loss": 0.5625,
|
| 1422 |
+
"step": 180
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.46647230320699706,
|
| 1426 |
+
"eval_loss": 0.5502737164497375,
|
| 1427 |
+
"eval_model_preparation_time": 0.0003,
|
| 1428 |
+
"eval_runtime": 24.6233,
|
| 1429 |
+
"eval_samples_per_second": 105.713,
|
| 1430 |
+
"eval_steps_per_second": 13.239,
|
| 1431 |
+
"step": 180
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.4690638160025915,
|
| 1435 |
+
"grad_norm": 2.34375,
|
| 1436 |
+
"learning_rate": 1.335647884903915e-05,
|
| 1437 |
+
"loss": 0.5492,
|
| 1438 |
+
"step": 181
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.47165532879818595,
|
| 1442 |
+
"grad_norm": 2.390625,
|
| 1443 |
+
"learning_rate": 1.3267994012560505e-05,
|
| 1444 |
+
"loss": 0.5493,
|
| 1445 |
+
"step": 182
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.4742468415937804,
|
| 1449 |
+
"grad_norm": 2.453125,
|
| 1450 |
+
"learning_rate": 1.3179221775131005e-05,
|
| 1451 |
+
"loss": 0.5508,
|
| 1452 |
+
"step": 183
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.4768383543893748,
|
| 1456 |
+
"grad_norm": 3.34375,
|
| 1457 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 1458 |
+
"loss": 0.5427,
|
| 1459 |
+
"step": 184
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.4794298671849692,
|
| 1463 |
+
"grad_norm": 2.078125,
|
| 1464 |
+
"learning_rate": 1.300084635000341e-05,
|
| 1465 |
+
"loss": 0.568,
|
| 1466 |
+
"step": 185
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.48202137998056366,
|
| 1470 |
+
"grad_norm": 2.15625,
|
| 1471 |
+
"learning_rate": 1.2911258849380199e-05,
|
| 1472 |
+
"loss": 0.5478,
|
| 1473 |
+
"step": 186
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.4846128927761581,
|
| 1477 |
+
"grad_norm": 2.15625,
|
| 1478 |
+
"learning_rate": 1.2821415320576309e-05,
|
| 1479 |
+
"loss": 0.5582,
|
| 1480 |
+
"step": 187
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.4872044055717525,
|
| 1484 |
+
"grad_norm": 3.0,
|
| 1485 |
+
"learning_rate": 1.273132366480438e-05,
|
| 1486 |
+
"loss": 0.5368,
|
| 1487 |
+
"step": 188
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.4897959183673469,
|
| 1491 |
+
"grad_norm": 2.71875,
|
| 1492 |
+
"learning_rate": 1.2640991805098369e-05,
|
| 1493 |
+
"loss": 0.5608,
|
| 1494 |
+
"step": 189
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.49238743116294137,
|
| 1498 |
+
"grad_norm": 2.203125,
|
| 1499 |
+
"learning_rate": 1.2550427685616767e-05,
|
| 1500 |
+
"loss": 0.5482,
|
| 1501 |
+
"step": 190
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.49238743116294137,
|
| 1505 |
+
"eval_loss": 0.547302782535553,
|
| 1506 |
+
"eval_model_preparation_time": 0.0003,
|
| 1507 |
+
"eval_runtime": 24.5429,
|
| 1508 |
+
"eval_samples_per_second": 106.059,
|
| 1509 |
+
"eval_steps_per_second": 13.283,
|
| 1510 |
+
"step": 190
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.4949789439585358,
|
| 1514 |
+
"grad_norm": 2.640625,
|
| 1515 |
+
"learning_rate": 1.2459639270943944e-05,
|
| 1516 |
+
"loss": 0.5508,
|
| 1517 |
+
"step": 191
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.4975704567541302,
|
| 1521 |
+
"grad_norm": 2.65625,
|
| 1522 |
+
"learning_rate": 1.2368634545389732e-05,
|
| 1523 |
+
"loss": 0.5402,
|
| 1524 |
+
"step": 192
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.5001619695497247,
|
| 1528 |
+
"grad_norm": 2.25,
|
| 1529 |
+
"learning_rate": 1.2277421512287227e-05,
|
| 1530 |
+
"loss": 0.5313,
|
| 1531 |
+
"step": 193
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.502753482345319,
|
| 1535 |
+
"grad_norm": 2.296875,
|
| 1536 |
+
"learning_rate": 1.2186008193288963e-05,
|
| 1537 |
+
"loss": 0.5535,
|
| 1538 |
+
"step": 194
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.5053449951409135,
|
| 1542 |
+
"grad_norm": 2.234375,
|
| 1543 |
+
"learning_rate": 1.2094402627661447e-05,
|
| 1544 |
+
"loss": 0.5375,
|
| 1545 |
+
"step": 195
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.5079365079365079,
|
| 1549 |
+
"grad_norm": 2.375,
|
| 1550 |
+
"learning_rate": 1.2002612871578143e-05,
|
| 1551 |
+
"loss": 0.5564,
|
| 1552 |
+
"step": 196
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.5105280207321024,
|
| 1556 |
+
"grad_norm": 2.5,
|
| 1557 |
+
"learning_rate": 1.1910646997411002e-05,
|
| 1558 |
+
"loss": 0.5459,
|
| 1559 |
+
"step": 197
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.5131195335276968,
|
| 1563 |
+
"grad_norm": 2.3125,
|
| 1564 |
+
"learning_rate": 1.1818513093020514e-05,
|
| 1565 |
+
"loss": 0.5545,
|
| 1566 |
+
"step": 198
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.5157110463232912,
|
| 1570 |
+
"grad_norm": 2.21875,
|
| 1571 |
+
"learning_rate": 1.172621926104446e-05,
|
| 1572 |
+
"loss": 0.535,
|
| 1573 |
+
"step": 199
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.5183025591188857,
|
| 1577 |
+
"grad_norm": 2.234375,
|
| 1578 |
+
"learning_rate": 1.1633773618185302e-05,
|
| 1579 |
+
"loss": 0.5469,
|
| 1580 |
+
"step": 200
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.5183025591188857,
|
| 1584 |
+
"eval_loss": 0.545219898223877,
|
| 1585 |
+
"eval_model_preparation_time": 0.0003,
|
| 1586 |
+
"eval_runtime": 24.4828,
|
| 1587 |
+
"eval_samples_per_second": 106.319,
|
| 1588 |
+
"eval_steps_per_second": 13.315,
|
| 1589 |
+
"step": 200
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.5208940719144801,
|
| 1593 |
+
"grad_norm": 2.203125,
|
| 1594 |
+
"learning_rate": 1.1541184294496393e-05,
|
| 1595 |
+
"loss": 0.5349,
|
| 1596 |
+
"step": 201
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.5234855847100746,
|
| 1600 |
+
"grad_norm": 2.46875,
|
| 1601 |
+
"learning_rate": 1.144845943266696e-05,
|
| 1602 |
+
"loss": 0.5271,
|
| 1603 |
+
"step": 202
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.5260770975056689,
|
| 1607 |
+
"grad_norm": 2.28125,
|
| 1608 |
+
"learning_rate": 1.1355607187306036e-05,
|
| 1609 |
+
"loss": 0.5431,
|
| 1610 |
+
"step": 203
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.5286686103012633,
|
| 1614 |
+
"grad_norm": 2.34375,
|
| 1615 |
+
"learning_rate": 1.1262635724225273e-05,
|
| 1616 |
+
"loss": 0.5344,
|
| 1617 |
+
"step": 204
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.5312601230968578,
|
| 1621 |
+
"grad_norm": 2.53125,
|
| 1622 |
+
"learning_rate": 1.1169553219720828e-05,
|
| 1623 |
+
"loss": 0.5386,
|
| 1624 |
+
"step": 205
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.5338516358924522,
|
| 1628 |
+
"grad_norm": 2.34375,
|
| 1629 |
+
"learning_rate": 1.1076367859854305e-05,
|
| 1630 |
+
"loss": 0.5277,
|
| 1631 |
+
"step": 206
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.5364431486880467,
|
| 1635 |
+
"grad_norm": 2.328125,
|
| 1636 |
+
"learning_rate": 1.0983087839732834e-05,
|
| 1637 |
+
"loss": 0.5339,
|
| 1638 |
+
"step": 207
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.5390346614836411,
|
| 1642 |
+
"grad_norm": 2.4375,
|
| 1643 |
+
"learning_rate": 1.0889721362788361e-05,
|
| 1644 |
+
"loss": 0.5535,
|
| 1645 |
+
"step": 208
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.5416261742792355,
|
| 1649 |
+
"grad_norm": 2.28125,
|
| 1650 |
+
"learning_rate": 1.0796276640056201e-05,
|
| 1651 |
+
"loss": 0.5385,
|
| 1652 |
+
"step": 209
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.54421768707483,
|
| 1656 |
+
"grad_norm": 2.3125,
|
| 1657 |
+
"learning_rate": 1.070276188945293e-05,
|
| 1658 |
+
"loss": 0.5628,
|
| 1659 |
+
"step": 210
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.54421768707483,
|
| 1663 |
+
"eval_loss": 0.5431892275810242,
|
| 1664 |
+
"eval_model_preparation_time": 0.0003,
|
| 1665 |
+
"eval_runtime": 24.5521,
|
| 1666 |
+
"eval_samples_per_second": 106.019,
|
| 1667 |
+
"eval_steps_per_second": 13.278,
|
| 1668 |
+
"step": 210
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.5468091998704243,
|
| 1672 |
+
"grad_norm": 2.140625,
|
| 1673 |
+
"learning_rate": 1.060918533505367e-05,
|
| 1674 |
+
"loss": 0.538,
|
| 1675 |
+
"step": 211
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.5494007126660188,
|
| 1679 |
+
"grad_norm": 3.1875,
|
| 1680 |
+
"learning_rate": 1.0515555206368815e-05,
|
| 1681 |
+
"loss": 0.53,
|
| 1682 |
+
"step": 212
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.5519922254616132,
|
| 1686 |
+
"grad_norm": 2.234375,
|
| 1687 |
+
"learning_rate": 1.0421879737620312e-05,
|
| 1688 |
+
"loss": 0.5315,
|
| 1689 |
+
"step": 213
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.5545837382572076,
|
| 1693 |
+
"grad_norm": 2.125,
|
| 1694 |
+
"learning_rate": 1.03281671670175e-05,
|
| 1695 |
+
"loss": 0.5408,
|
| 1696 |
+
"step": 214
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.5571752510528021,
|
| 1700 |
+
"grad_norm": 2.4375,
|
| 1701 |
+
"learning_rate": 1.0234425736032607e-05,
|
| 1702 |
+
"loss": 0.5436,
|
| 1703 |
+
"step": 215
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.5597667638483965,
|
| 1707 |
+
"grad_norm": 2.40625,
|
| 1708 |
+
"learning_rate": 1.014066368867596e-05,
|
| 1709 |
+
"loss": 0.5269,
|
| 1710 |
+
"step": 216
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.562358276643991,
|
| 1714 |
+
"grad_norm": 2.125,
|
| 1715 |
+
"learning_rate": 1.0046889270770987e-05,
|
| 1716 |
+
"loss": 0.5412,
|
| 1717 |
+
"step": 217
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.5649497894395854,
|
| 1721 |
+
"grad_norm": 2.3125,
|
| 1722 |
+
"learning_rate": 9.953110729229018e-06,
|
| 1723 |
+
"loss": 0.5346,
|
| 1724 |
+
"step": 218
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.5675413022351797,
|
| 1728 |
+
"grad_norm": 2.109375,
|
| 1729 |
+
"learning_rate": 9.859336311324042e-06,
|
| 1730 |
+
"loss": 0.5435,
|
| 1731 |
+
"step": 219
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.5701328150307742,
|
| 1735 |
+
"grad_norm": 2.125,
|
| 1736 |
+
"learning_rate": 9.765574263967397e-06,
|
| 1737 |
+
"loss": 0.5482,
|
| 1738 |
+
"step": 220
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.5701328150307742,
|
| 1742 |
+
"eval_loss": 0.5415154695510864,
|
| 1743 |
+
"eval_model_preparation_time": 0.0003,
|
| 1744 |
+
"eval_runtime": 24.571,
|
| 1745 |
+
"eval_samples_per_second": 105.938,
|
| 1746 |
+
"eval_steps_per_second": 13.268,
|
| 1747 |
+
"step": 220
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.5727243278263686,
|
| 1751 |
+
"grad_norm": 2.21875,
|
| 1752 |
+
"learning_rate": 9.671832832982502e-06,
|
| 1753 |
+
"loss": 0.5401,
|
| 1754 |
+
"step": 221
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.5753158406219631,
|
| 1758 |
+
"grad_norm": 2.3125,
|
| 1759 |
+
"learning_rate": 9.57812026237969e-06,
|
| 1760 |
+
"loss": 0.5359,
|
| 1761 |
+
"step": 222
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.5779073534175575,
|
| 1765 |
+
"grad_norm": 2.375,
|
| 1766 |
+
"learning_rate": 9.484444793631186e-06,
|
| 1767 |
+
"loss": 0.5366,
|
| 1768 |
+
"step": 223
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.5804988662131519,
|
| 1772 |
+
"grad_norm": 2.09375,
|
| 1773 |
+
"learning_rate": 9.390814664946332e-06,
|
| 1774 |
+
"loss": 0.5343,
|
| 1775 |
+
"step": 224
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.5830903790087464,
|
| 1779 |
+
"grad_norm": 2.03125,
|
| 1780 |
+
"learning_rate": 9.297238110547075e-06,
|
| 1781 |
+
"loss": 0.5385,
|
| 1782 |
+
"step": 225
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.5856818918043408,
|
| 1786 |
+
"grad_norm": 2.21875,
|
| 1787 |
+
"learning_rate": 9.203723359943802e-06,
|
| 1788 |
+
"loss": 0.5473,
|
| 1789 |
+
"step": 226
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.5882734045999352,
|
| 1793 |
+
"grad_norm": 2.53125,
|
| 1794 |
+
"learning_rate": 9.110278637211642e-06,
|
| 1795 |
+
"loss": 0.5316,
|
| 1796 |
+
"step": 227
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.5908649173955296,
|
| 1800 |
+
"grad_norm": 2.046875,
|
| 1801 |
+
"learning_rate": 9.016912160267168e-06,
|
| 1802 |
+
"loss": 0.53,
|
| 1803 |
+
"step": 228
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.593456430191124,
|
| 1807 |
+
"grad_norm": 2.4375,
|
| 1808 |
+
"learning_rate": 8.923632140145702e-06,
|
| 1809 |
+
"loss": 0.5497,
|
| 1810 |
+
"step": 229
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.5960479429867185,
|
| 1814 |
+
"grad_norm": 2.15625,
|
| 1815 |
+
"learning_rate": 8.830446780279175e-06,
|
| 1816 |
+
"loss": 0.5499,
|
| 1817 |
+
"step": 230
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.5960479429867185,
|
| 1821 |
+
"eval_loss": 0.5400256514549255,
|
| 1822 |
+
"eval_model_preparation_time": 0.0003,
|
| 1823 |
+
"eval_runtime": 24.5551,
|
| 1824 |
+
"eval_samples_per_second": 106.007,
|
| 1825 |
+
"eval_steps_per_second": 13.276,
|
| 1826 |
+
"step": 230
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.5986394557823129,
|
| 1830 |
+
"grad_norm": 2.15625,
|
| 1831 |
+
"learning_rate": 8.73736427577473e-06,
|
| 1832 |
+
"loss": 0.5301,
|
| 1833 |
+
"step": 231
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.6012309685779074,
|
| 1837 |
+
"grad_norm": 2.171875,
|
| 1838 |
+
"learning_rate": 8.644392812693969e-06,
|
| 1839 |
+
"loss": 0.5542,
|
| 1840 |
+
"step": 232
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 0.6038224813735018,
|
| 1844 |
+
"grad_norm": 2.1875,
|
| 1845 |
+
"learning_rate": 8.551540567333041e-06,
|
| 1846 |
+
"loss": 0.5374,
|
| 1847 |
+
"step": 233
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.6064139941690962,
|
| 1851 |
+
"grad_norm": 2.421875,
|
| 1852 |
+
"learning_rate": 8.458815705503612e-06,
|
| 1853 |
+
"loss": 0.549,
|
| 1854 |
+
"step": 234
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.6090055069646907,
|
| 1858 |
+
"grad_norm": 2.0625,
|
| 1859 |
+
"learning_rate": 8.366226381814698e-06,
|
| 1860 |
+
"loss": 0.5383,
|
| 1861 |
+
"step": 235
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.611597019760285,
|
| 1865 |
+
"grad_norm": 2.203125,
|
| 1866 |
+
"learning_rate": 8.273780738955545e-06,
|
| 1867 |
+
"loss": 0.5297,
|
| 1868 |
+
"step": 236
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.6141885325558795,
|
| 1872 |
+
"grad_norm": 2.140625,
|
| 1873 |
+
"learning_rate": 8.181486906979488e-06,
|
| 1874 |
+
"loss": 0.5303,
|
| 1875 |
+
"step": 237
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.6167800453514739,
|
| 1879 |
+
"grad_norm": 2.109375,
|
| 1880 |
+
"learning_rate": 8.089353002589003e-06,
|
| 1881 |
+
"loss": 0.5429,
|
| 1882 |
+
"step": 238
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.6193715581470683,
|
| 1886 |
+
"grad_norm": 2.171875,
|
| 1887 |
+
"learning_rate": 7.997387128421859e-06,
|
| 1888 |
+
"loss": 0.5442,
|
| 1889 |
+
"step": 239
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.6219630709426628,
|
| 1893 |
+
"grad_norm": 2.328125,
|
| 1894 |
+
"learning_rate": 7.905597372338558e-06,
|
| 1895 |
+
"loss": 0.5451,
|
| 1896 |
+
"step": 240
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.6219630709426628,
|
| 1900 |
+
"eval_loss": 0.5389755964279175,
|
| 1901 |
+
"eval_model_preparation_time": 0.0003,
|
| 1902 |
+
"eval_runtime": 24.5608,
|
| 1903 |
+
"eval_samples_per_second": 105.982,
|
| 1904 |
+
"eval_steps_per_second": 13.273,
|
| 1905 |
+
"step": 240
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.6245545837382572,
|
| 1909 |
+
"grad_norm": 2.078125,
|
| 1910 |
+
"learning_rate": 7.81399180671104e-06,
|
| 1911 |
+
"loss": 0.5392,
|
| 1912 |
+
"step": 241
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.6271460965338517,
|
| 1916 |
+
"grad_norm": 2.140625,
|
| 1917 |
+
"learning_rate": 7.722578487712776e-06,
|
| 1918 |
+
"loss": 0.5303,
|
| 1919 |
+
"step": 242
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.6297376093294461,
|
| 1923 |
+
"grad_norm": 2.15625,
|
| 1924 |
+
"learning_rate": 7.631365454610273e-06,
|
| 1925 |
+
"loss": 0.5387,
|
| 1926 |
+
"step": 243
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.6323291221250404,
|
| 1930 |
+
"grad_norm": 2.265625,
|
| 1931 |
+
"learning_rate": 7.540360729056059e-06,
|
| 1932 |
+
"loss": 0.5528,
|
| 1933 |
+
"step": 244
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.6349206349206349,
|
| 1937 |
+
"grad_norm": 2.15625,
|
| 1938 |
+
"learning_rate": 7.449572314383237e-06,
|
| 1939 |
+
"loss": 0.5488,
|
| 1940 |
+
"step": 245
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.6375121477162293,
|
| 1944 |
+
"grad_norm": 2.03125,
|
| 1945 |
+
"learning_rate": 7.359008194901633e-06,
|
| 1946 |
+
"loss": 0.5216,
|
| 1947 |
+
"step": 246
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.6401036605118238,
|
| 1951 |
+
"grad_norm": 2.15625,
|
| 1952 |
+
"learning_rate": 7.268676335195624e-06,
|
| 1953 |
+
"loss": 0.5314,
|
| 1954 |
+
"step": 247
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.6426951733074182,
|
| 1958 |
+
"grad_norm": 2.125,
|
| 1959 |
+
"learning_rate": 7.1785846794236945e-06,
|
| 1960 |
+
"loss": 0.5411,
|
| 1961 |
+
"step": 248
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.6452866861030127,
|
| 1965 |
+
"grad_norm": 2.140625,
|
| 1966 |
+
"learning_rate": 7.088741150619804e-06,
|
| 1967 |
+
"loss": 0.5272,
|
| 1968 |
+
"step": 249
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.6478781988986071,
|
| 1972 |
+
"grad_norm": 2.125,
|
| 1973 |
+
"learning_rate": 6.999153649996595e-06,
|
| 1974 |
+
"loss": 0.5344,
|
| 1975 |
+
"step": 250
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.6478781988986071,
|
| 1979 |
+
"eval_loss": 0.538066029548645,
|
| 1980 |
+
"eval_model_preparation_time": 0.0003,
|
| 1981 |
+
"eval_runtime": 24.5108,
|
| 1982 |
+
"eval_samples_per_second": 106.198,
|
| 1983 |
+
"eval_steps_per_second": 13.3,
|
| 1984 |
+
"step": 250
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.6504697116942015,
|
| 1988 |
+
"grad_norm": 2.09375,
|
| 1989 |
+
"learning_rate": 6.909830056250527e-06,
|
| 1990 |
+
"loss": 0.532,
|
| 1991 |
+
"step": 251
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.6530612244897959,
|
| 1995 |
+
"grad_norm": 2.09375,
|
| 1996 |
+
"learning_rate": 6.820778224868998e-06,
|
| 1997 |
+
"loss": 0.5376,
|
| 1998 |
+
"step": 252
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.6556527372853903,
|
| 2002 |
+
"grad_norm": 2.15625,
|
| 2003 |
+
"learning_rate": 6.732005987439494e-06,
|
| 2004 |
+
"loss": 0.5501,
|
| 2005 |
+
"step": 253
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.6582442500809847,
|
| 2009 |
+
"grad_norm": 2.0625,
|
| 2010 |
+
"learning_rate": 6.6435211509608546e-06,
|
| 2011 |
+
"loss": 0.532,
|
| 2012 |
+
"step": 254
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.6608357628765792,
|
| 2016 |
+
"grad_norm": 2.3125,
|
| 2017 |
+
"learning_rate": 6.555331497156671e-06,
|
| 2018 |
+
"loss": 0.5406,
|
| 2019 |
+
"step": 255
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.6634272756721736,
|
| 2023 |
+
"grad_norm": 2.03125,
|
| 2024 |
+
"learning_rate": 6.467444781790967e-06,
|
| 2025 |
+
"loss": 0.5249,
|
| 2026 |
+
"step": 256
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.6660187884677681,
|
| 2030 |
+
"grad_norm": 2.171875,
|
| 2031 |
+
"learning_rate": 6.379868733986089e-06,
|
| 2032 |
+
"loss": 0.5195,
|
| 2033 |
+
"step": 257
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.6686103012633625,
|
| 2037 |
+
"grad_norm": 2.1875,
|
| 2038 |
+
"learning_rate": 6.292611055542998e-06,
|
| 2039 |
+
"loss": 0.5397,
|
| 2040 |
+
"step": 258
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.671201814058957,
|
| 2044 |
+
"grad_norm": 2.21875,
|
| 2045 |
+
"learning_rate": 6.205679420263917e-06,
|
| 2046 |
+
"loss": 0.5455,
|
| 2047 |
+
"step": 259
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.6737933268545514,
|
| 2051 |
+
"grad_norm": 2.09375,
|
| 2052 |
+
"learning_rate": 6.119081473277502e-06,
|
| 2053 |
+
"loss": 0.5414,
|
| 2054 |
+
"step": 260
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.6737933268545514,
|
| 2058 |
+
"eval_loss": 0.5372032523155212,
|
| 2059 |
+
"eval_model_preparation_time": 0.0003,
|
| 2060 |
+
"eval_runtime": 24.5567,
|
| 2061 |
+
"eval_samples_per_second": 106.0,
|
| 2062 |
+
"eval_steps_per_second": 13.275,
|
| 2063 |
+
"step": 260
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 0.6763848396501457,
|
| 2067 |
+
"grad_norm": 2.5,
|
| 2068 |
+
"learning_rate": 6.032824830366466e-06,
|
| 2069 |
+
"loss": 0.5398,
|
| 2070 |
+
"step": 261
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 0.6789763524457402,
|
| 2074 |
+
"grad_norm": 2.109375,
|
| 2075 |
+
"learning_rate": 5.946917077297819e-06,
|
| 2076 |
+
"loss": 0.5512,
|
| 2077 |
+
"step": 262
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 0.6815678652413346,
|
| 2081 |
+
"grad_norm": 2.125,
|
| 2082 |
+
"learning_rate": 5.86136576915576e-06,
|
| 2083 |
+
"loss": 0.5486,
|
| 2084 |
+
"step": 263
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.6841593780369291,
|
| 2088 |
+
"grad_norm": 2.203125,
|
| 2089 |
+
"learning_rate": 5.7761784296772395e-06,
|
| 2090 |
+
"loss": 0.543,
|
| 2091 |
+
"step": 264
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.6867508908325235,
|
| 2095 |
+
"grad_norm": 2.171875,
|
| 2096 |
+
"learning_rate": 5.6913625505902966e-06,
|
| 2097 |
+
"loss": 0.5065,
|
| 2098 |
+
"step": 265
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 0.6893424036281179,
|
| 2102 |
+
"grad_norm": 2.171875,
|
| 2103 |
+
"learning_rate": 5.6069255909551986e-06,
|
| 2104 |
+
"loss": 0.5328,
|
| 2105 |
+
"step": 266
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 0.6919339164237124,
|
| 2109 |
+
"grad_norm": 2.015625,
|
| 2110 |
+
"learning_rate": 5.522874976508464e-06,
|
| 2111 |
+
"loss": 0.5404,
|
| 2112 |
+
"step": 267
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 0.6945254292193068,
|
| 2116 |
+
"grad_norm": 1.9375,
|
| 2117 |
+
"learning_rate": 5.439218099009822e-06,
|
| 2118 |
+
"loss": 0.528,
|
| 2119 |
+
"step": 268
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 0.6971169420149012,
|
| 2123 |
+
"grad_norm": 2.0625,
|
| 2124 |
+
"learning_rate": 5.355962315592118e-06,
|
| 2125 |
+
"loss": 0.5377,
|
| 2126 |
+
"step": 269
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.6997084548104956,
|
| 2130 |
+
"grad_norm": 2.078125,
|
| 2131 |
+
"learning_rate": 5.273114948114346e-06,
|
| 2132 |
+
"loss": 0.5361,
|
| 2133 |
+
"step": 270
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.6997084548104956,
|
| 2137 |
+
"eval_loss": 0.5366343259811401,
|
| 2138 |
+
"eval_model_preparation_time": 0.0003,
|
| 2139 |
+
"eval_runtime": 24.5782,
|
| 2140 |
+
"eval_samples_per_second": 105.907,
|
| 2141 |
+
"eval_steps_per_second": 13.264,
|
| 2142 |
+
"step": 270
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.70229996760609,
|
| 2146 |
+
"grad_norm": 2.203125,
|
| 2147 |
+
"learning_rate": 5.190683282517701e-06,
|
| 2148 |
+
"loss": 0.5295,
|
| 2149 |
+
"step": 271
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 0.7048914804016845,
|
| 2153 |
+
"grad_norm": 2.15625,
|
| 2154 |
+
"learning_rate": 5.108674568184822e-06,
|
| 2155 |
+
"loss": 0.5333,
|
| 2156 |
+
"step": 272
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.7074829931972789,
|
| 2160 |
+
"grad_norm": 2.0,
|
| 2161 |
+
"learning_rate": 5.027096017302261e-06,
|
| 2162 |
+
"loss": 0.525,
|
| 2163 |
+
"step": 273
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.7100745059928734,
|
| 2167 |
+
"grad_norm": 2.140625,
|
| 2168 |
+
"learning_rate": 4.945954804226214e-06,
|
| 2169 |
+
"loss": 0.5328,
|
| 2170 |
+
"step": 274
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.7126660187884678,
|
| 2174 |
+
"grad_norm": 1.953125,
|
| 2175 |
+
"learning_rate": 4.865258064851579e-06,
|
| 2176 |
+
"loss": 0.5453,
|
| 2177 |
+
"step": 275
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 0.7152575315840622,
|
| 2181 |
+
"grad_norm": 2.109375,
|
| 2182 |
+
"learning_rate": 4.785012895984397e-06,
|
| 2183 |
+
"loss": 0.537,
|
| 2184 |
+
"step": 276
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 0.7178490443796566,
|
| 2188 |
+
"grad_norm": 1.9609375,
|
| 2189 |
+
"learning_rate": 4.705226354717704e-06,
|
| 2190 |
+
"loss": 0.5459,
|
| 2191 |
+
"step": 277
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 0.720440557175251,
|
| 2195 |
+
"grad_norm": 1.9296875,
|
| 2196 |
+
"learning_rate": 4.625905457810943e-06,
|
| 2197 |
+
"loss": 0.5444,
|
| 2198 |
+
"step": 278
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.7230320699708455,
|
| 2202 |
+
"grad_norm": 2.25,
|
| 2203 |
+
"learning_rate": 4.547057181072861e-06,
|
| 2204 |
+
"loss": 0.532,
|
| 2205 |
+
"step": 279
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.7256235827664399,
|
| 2209 |
+
"grad_norm": 2.046875,
|
| 2210 |
+
"learning_rate": 4.468688458748006e-06,
|
| 2211 |
+
"loss": 0.5209,
|
| 2212 |
+
"step": 280
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 0.7256235827664399,
|
| 2216 |
+
"eval_loss": 0.5361185073852539,
|
| 2217 |
+
"eval_model_preparation_time": 0.0003,
|
| 2218 |
+
"eval_runtime": 24.5554,
|
| 2219 |
+
"eval_samples_per_second": 106.005,
|
| 2220 |
+
"eval_steps_per_second": 13.276,
|
| 2221 |
+
"step": 280
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.7282150955620343,
|
| 2225 |
+
"grad_norm": 1.9375,
|
| 2226 |
+
"learning_rate": 4.390806182906946e-06,
|
| 2227 |
+
"loss": 0.5304,
|
| 2228 |
+
"step": 281
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.7308066083576288,
|
| 2232 |
+
"grad_norm": 1.9921875,
|
| 2233 |
+
"learning_rate": 4.313417202840106e-06,
|
| 2234 |
+
"loss": 0.5532,
|
| 2235 |
+
"step": 282
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.7333981211532232,
|
| 2239 |
+
"grad_norm": 2.265625,
|
| 2240 |
+
"learning_rate": 4.2365283244554545e-06,
|
| 2241 |
+
"loss": 0.5358,
|
| 2242 |
+
"step": 283
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.7359896339488177,
|
| 2246 |
+
"grad_norm": 2.34375,
|
| 2247 |
+
"learning_rate": 4.160146309679928e-06,
|
| 2248 |
+
"loss": 0.5444,
|
| 2249 |
+
"step": 284
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.738581146744412,
|
| 2253 |
+
"grad_norm": 2.171875,
|
| 2254 |
+
"learning_rate": 4.084277875864776e-06,
|
| 2255 |
+
"loss": 0.5374,
|
| 2256 |
+
"step": 285
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.7411726595400064,
|
| 2260 |
+
"grad_norm": 2.53125,
|
| 2261 |
+
"learning_rate": 4.008929695194819e-06,
|
| 2262 |
+
"loss": 0.5441,
|
| 2263 |
+
"step": 286
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.7437641723356009,
|
| 2267 |
+
"grad_norm": 2.71875,
|
| 2268 |
+
"learning_rate": 3.934108394101645e-06,
|
| 2269 |
+
"loss": 0.5383,
|
| 2270 |
+
"step": 287
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.7463556851311953,
|
| 2274 |
+
"grad_norm": 2.3125,
|
| 2275 |
+
"learning_rate": 3.859820552680867e-06,
|
| 2276 |
+
"loss": 0.5481,
|
| 2277 |
+
"step": 288
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.7489471979267898,
|
| 2281 |
+
"grad_norm": 2.359375,
|
| 2282 |
+
"learning_rate": 3.786072704113456e-06,
|
| 2283 |
+
"loss": 0.5435,
|
| 2284 |
+
"step": 289
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.7515387107223842,
|
| 2288 |
+
"grad_norm": 2.0,
|
| 2289 |
+
"learning_rate": 3.712871334091154e-06,
|
| 2290 |
+
"loss": 0.5247,
|
| 2291 |
+
"step": 290
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.7515387107223842,
|
| 2295 |
+
"eval_loss": 0.5358829498291016,
|
| 2296 |
+
"eval_model_preparation_time": 0.0003,
|
| 2297 |
+
"eval_runtime": 24.5374,
|
| 2298 |
+
"eval_samples_per_second": 106.083,
|
| 2299 |
+
"eval_steps_per_second": 13.286,
|
| 2300 |
+
"step": 290
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.7541302235179786,
|
| 2304 |
+
"grad_norm": 2.03125,
|
| 2305 |
+
"learning_rate": 3.640222880246117e-06,
|
| 2306 |
+
"loss": 0.5215,
|
| 2307 |
+
"step": 291
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.7567217363135731,
|
| 2311 |
+
"grad_norm": 2.09375,
|
| 2312 |
+
"learning_rate": 3.5681337315847677e-06,
|
| 2313 |
+
"loss": 0.5337,
|
| 2314 |
+
"step": 292
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.7593132491091675,
|
| 2318 |
+
"grad_norm": 1.9609375,
|
| 2319 |
+
"learning_rate": 3.4966102279258964e-06,
|
| 2320 |
+
"loss": 0.5353,
|
| 2321 |
+
"step": 293
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.7619047619047619,
|
| 2325 |
+
"grad_norm": 1.984375,
|
| 2326 |
+
"learning_rate": 3.425658659343141e-06,
|
| 2327 |
+
"loss": 0.5454,
|
| 2328 |
+
"step": 294
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 0.7644962747003563,
|
| 2332 |
+
"grad_norm": 2.046875,
|
| 2333 |
+
"learning_rate": 3.355285265611784e-06,
|
| 2334 |
+
"loss": 0.5172,
|
| 2335 |
+
"step": 295
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 0.7670877874959507,
|
| 2339 |
+
"grad_norm": 1.9765625,
|
| 2340 |
+
"learning_rate": 3.285496235660013e-06,
|
| 2341 |
+
"loss": 0.5267,
|
| 2342 |
+
"step": 296
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.7696793002915452,
|
| 2346 |
+
"grad_norm": 1.9765625,
|
| 2347 |
+
"learning_rate": 3.216297707024655e-06,
|
| 2348 |
+
"loss": 0.5436,
|
| 2349 |
+
"step": 297
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.7722708130871396,
|
| 2353 |
+
"grad_norm": 2.1875,
|
| 2354 |
+
"learning_rate": 3.147695765311377e-06,
|
| 2355 |
+
"loss": 0.5349,
|
| 2356 |
+
"step": 298
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.7748623258827341,
|
| 2360 |
+
"grad_norm": 2.0,
|
| 2361 |
+
"learning_rate": 3.079696443659538e-06,
|
| 2362 |
+
"loss": 0.5437,
|
| 2363 |
+
"step": 299
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 0.7774538386783285,
|
| 2367 |
+
"grad_norm": 2.046875,
|
| 2368 |
+
"learning_rate": 3.0123057222115835e-06,
|
| 2369 |
+
"loss": 0.5185,
|
| 2370 |
+
"step": 300
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 0.7774538386783285,
|
| 2374 |
+
"eval_loss": 0.5356724858283997,
|
| 2375 |
+
"eval_model_preparation_time": 0.0003,
|
| 2376 |
+
"eval_runtime": 24.5736,
|
| 2377 |
+
"eval_samples_per_second": 105.927,
|
| 2378 |
+
"eval_steps_per_second": 13.266,
|
| 2379 |
+
"step": 300
|
| 2380 |
+
}
|
| 2381 |
+
],
|
| 2382 |
+
"logging_steps": 1,
|
| 2383 |
+
"max_steps": 385,
|
| 2384 |
+
"num_input_tokens_seen": 0,
|
| 2385 |
+
"num_train_epochs": 1,
|
| 2386 |
+
"save_steps": 100,
|
| 2387 |
+
"stateful_callbacks": {
|
| 2388 |
+
"TrainerControl": {
|
| 2389 |
+
"args": {
|
| 2390 |
+
"should_epoch_stop": false,
|
| 2391 |
+
"should_evaluate": false,
|
| 2392 |
+
"should_log": false,
|
| 2393 |
+
"should_save": true,
|
| 2394 |
+
"should_training_stop": false
|
| 2395 |
+
},
|
| 2396 |
+
"attributes": {}
|
| 2397 |
+
}
|
| 2398 |
+
},
|
| 2399 |
+
"total_flos": 8.3477252800512e+16,
|
| 2400 |
+
"train_batch_size": 8,
|
| 2401 |
+
"trial_name": null,
|
| 2402 |
+
"trial_params": null
|
| 2403 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca15ebb16a59dc055f8ae01b1eb1038e869a6556aa3b7b802c58f2dde6a2993c
|
| 3 |
+
size 5304
|
checkpoint-385/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322b2d3fc9de58487c02f1cd651d484d73244f9704de3d5feea36d002a38af0f
|
| 3 |
+
size 748
|
checkpoint-385/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82bdd024a0ba026e4001e0433d3922a27b1242913db7be87e2851d17165b99c8
|
| 3 |
+
size 111
|
checkpoint-385/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:783f210de0e18c0cadd41c5bb8b4d1bbf18230cf2d1546ebf37450c870ceee8d
|
| 3 |
+
size 810702192
|
checkpoint-385/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5d12293b5ce20e50619268243be579e5275bbe8d306cf25e741072c12661697
|
| 3 |
+
size 1621580026
|
checkpoint-385/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:358ab1e5c417d33e0932059d98ea2c06804bddb23da73a96b2bf00951951b130
|
| 3 |
+
size 14244
|
checkpoint-385/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08507fbaf34837c4bf6230303cd0aebaa835a7789433f0db443e7ed81a9694d5
|
| 3 |
+
size 1064
|
checkpoint-385/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8
|
| 3 |
+
size 473
|
checkpoint-385/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870f4e2baa6b683221fa52004d5d6f40ab8c9d31961617304b78c910c2c3caf2
|
| 3 |
+
size 2114042
|
checkpoint-385/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c4f587ac3a67c3964d3e84248f95ffc8e4f0e64d9de677692df39aa35eb2d11
|
| 3 |
+
size 4845
|
checkpoint-385/trainer_state.json
ADDED
|
@@ -0,0 +1,3070 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9977324263038548,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 385,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0025915127955944283,
|
| 13 |
+
"grad_norm": 12.625,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.7977,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0051830255911888565,
|
| 20 |
+
"grad_norm": 12.0625,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.7787,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.007774538386783284,
|
| 27 |
+
"grad_norm": 13.0,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.8003,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.010366051182377713,
|
| 34 |
+
"grad_norm": 12.5625,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.787,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01295756397797214,
|
| 41 |
+
"grad_norm": 12.25,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.7684,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.015549076773566569,
|
| 48 |
+
"grad_norm": 12.625,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.7544,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.018140589569160998,
|
| 55 |
+
"grad_norm": 12.5,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.7769,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.020732102364755426,
|
| 62 |
+
"grad_norm": 11.4375,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.7161,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.023323615160349854,
|
| 69 |
+
"grad_norm": 11.5,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.7165,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02591512795594428,
|
| 76 |
+
"grad_norm": 12.1875,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.7437,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02591512795594428,
|
| 83 |
+
"eval_loss": 1.7256978750228882,
|
| 84 |
+
"eval_model_preparation_time": 0.0003,
|
| 85 |
+
"eval_runtime": 24.5814,
|
| 86 |
+
"eval_samples_per_second": 105.893,
|
| 87 |
+
"eval_steps_per_second": 13.262,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.02850664075153871,
|
| 92 |
+
"grad_norm": 11.4375,
|
| 93 |
+
"learning_rate": 4.4e-06,
|
| 94 |
+
"loss": 1.7068,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.031098153547133137,
|
| 99 |
+
"grad_norm": 11.75,
|
| 100 |
+
"learning_rate": 4.800000000000001e-06,
|
| 101 |
+
"loss": 1.688,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.03368966634272757,
|
| 106 |
+
"grad_norm": 11.6875,
|
| 107 |
+
"learning_rate": 5.2e-06,
|
| 108 |
+
"loss": 1.6602,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.036281179138321996,
|
| 113 |
+
"grad_norm": 11.5625,
|
| 114 |
+
"learning_rate": 5.600000000000001e-06,
|
| 115 |
+
"loss": 1.6389,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.038872691933916424,
|
| 120 |
+
"grad_norm": 10.75,
|
| 121 |
+
"learning_rate": 6e-06,
|
| 122 |
+
"loss": 1.6228,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.04146420472951085,
|
| 127 |
+
"grad_norm": 10.8125,
|
| 128 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 129 |
+
"loss": 1.5823,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.04405571752510528,
|
| 134 |
+
"grad_norm": 9.5625,
|
| 135 |
+
"learning_rate": 6.800000000000001e-06,
|
| 136 |
+
"loss": 1.5134,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.04664723032069971,
|
| 141 |
+
"grad_norm": 9.125,
|
| 142 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 143 |
+
"loss": 1.4833,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.049238743116294136,
|
| 148 |
+
"grad_norm": 7.375,
|
| 149 |
+
"learning_rate": 7.600000000000001e-06,
|
| 150 |
+
"loss": 1.4966,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.05183025591188856,
|
| 155 |
+
"grad_norm": 7.0,
|
| 156 |
+
"learning_rate": 8.000000000000001e-06,
|
| 157 |
+
"loss": 1.4653,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.05183025591188856,
|
| 162 |
+
"eval_loss": 1.4041186571121216,
|
| 163 |
+
"eval_model_preparation_time": 0.0003,
|
| 164 |
+
"eval_runtime": 24.6226,
|
| 165 |
+
"eval_samples_per_second": 105.716,
|
| 166 |
+
"eval_steps_per_second": 13.24,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.05442176870748299,
|
| 171 |
+
"grad_norm": 6.0625,
|
| 172 |
+
"learning_rate": 8.400000000000001e-06,
|
| 173 |
+
"loss": 1.3844,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.05701328150307742,
|
| 178 |
+
"grad_norm": 5.375,
|
| 179 |
+
"learning_rate": 8.8e-06,
|
| 180 |
+
"loss": 1.3735,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05960479429867185,
|
| 185 |
+
"grad_norm": 5.09375,
|
| 186 |
+
"learning_rate": 9.200000000000002e-06,
|
| 187 |
+
"loss": 1.3281,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.062196307094266275,
|
| 192 |
+
"grad_norm": 5.25,
|
| 193 |
+
"learning_rate": 9.600000000000001e-06,
|
| 194 |
+
"loss": 1.2837,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.06478781988986071,
|
| 199 |
+
"grad_norm": 5.25,
|
| 200 |
+
"learning_rate": 1e-05,
|
| 201 |
+
"loss": 1.2777,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.06737933268545514,
|
| 206 |
+
"grad_norm": 5.03125,
|
| 207 |
+
"learning_rate": 1.04e-05,
|
| 208 |
+
"loss": 1.2465,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.06997084548104957,
|
| 213 |
+
"grad_norm": 5.0625,
|
| 214 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 215 |
+
"loss": 1.2041,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.07256235827664399,
|
| 220 |
+
"grad_norm": 4.9375,
|
| 221 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 222 |
+
"loss": 1.1524,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.07515387107223842,
|
| 227 |
+
"grad_norm": 4.65625,
|
| 228 |
+
"learning_rate": 1.16e-05,
|
| 229 |
+
"loss": 1.1491,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.07774538386783285,
|
| 234 |
+
"grad_norm": 5.125,
|
| 235 |
+
"learning_rate": 1.2e-05,
|
| 236 |
+
"loss": 1.127,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.07774538386783285,
|
| 241 |
+
"eval_loss": 1.105301856994629,
|
| 242 |
+
"eval_model_preparation_time": 0.0003,
|
| 243 |
+
"eval_runtime": 24.5195,
|
| 244 |
+
"eval_samples_per_second": 106.161,
|
| 245 |
+
"eval_steps_per_second": 13.296,
|
| 246 |
+
"step": 30
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.08033689666342728,
|
| 250 |
+
"grad_norm": 5.09375,
|
| 251 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 252 |
+
"loss": 1.0993,
|
| 253 |
+
"step": 31
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.0829284094590217,
|
| 257 |
+
"grad_norm": 4.9375,
|
| 258 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 259 |
+
"loss": 1.0637,
|
| 260 |
+
"step": 32
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.08551992225461613,
|
| 264 |
+
"grad_norm": 4.75,
|
| 265 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 266 |
+
"loss": 1.0447,
|
| 267 |
+
"step": 33
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.08811143505021056,
|
| 271 |
+
"grad_norm": 5.21875,
|
| 272 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 273 |
+
"loss": 1.047,
|
| 274 |
+
"step": 34
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.09070294784580499,
|
| 278 |
+
"grad_norm": 4.9375,
|
| 279 |
+
"learning_rate": 1.4e-05,
|
| 280 |
+
"loss": 0.9841,
|
| 281 |
+
"step": 35
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.09329446064139942,
|
| 285 |
+
"grad_norm": 4.90625,
|
| 286 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 287 |
+
"loss": 0.9735,
|
| 288 |
+
"step": 36
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.09588597343699384,
|
| 292 |
+
"grad_norm": 5.71875,
|
| 293 |
+
"learning_rate": 1.48e-05,
|
| 294 |
+
"loss": 0.9409,
|
| 295 |
+
"step": 37
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.09847748623258827,
|
| 299 |
+
"grad_norm": 5.0625,
|
| 300 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 301 |
+
"loss": 0.9108,
|
| 302 |
+
"step": 38
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.1010689990281827,
|
| 306 |
+
"grad_norm": 4.90625,
|
| 307 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 308 |
+
"loss": 0.9029,
|
| 309 |
+
"step": 39
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.10366051182377713,
|
| 313 |
+
"grad_norm": 5.0625,
|
| 314 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 315 |
+
"loss": 0.8938,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.10366051182377713,
|
| 320 |
+
"eval_loss": 0.8692858815193176,
|
| 321 |
+
"eval_model_preparation_time": 0.0003,
|
| 322 |
+
"eval_runtime": 24.5016,
|
| 323 |
+
"eval_samples_per_second": 106.238,
|
| 324 |
+
"eval_steps_per_second": 13.305,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.10625202461937155,
|
| 329 |
+
"grad_norm": 5.125,
|
| 330 |
+
"learning_rate": 1.64e-05,
|
| 331 |
+
"loss": 0.8501,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.10884353741496598,
|
| 336 |
+
"grad_norm": 4.53125,
|
| 337 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 338 |
+
"loss": 0.8545,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.11143505021056041,
|
| 343 |
+
"grad_norm": 5.1875,
|
| 344 |
+
"learning_rate": 1.72e-05,
|
| 345 |
+
"loss": 0.8169,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.11402656300615484,
|
| 350 |
+
"grad_norm": 4.5,
|
| 351 |
+
"learning_rate": 1.76e-05,
|
| 352 |
+
"loss": 0.8102,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.11661807580174927,
|
| 357 |
+
"grad_norm": 4.3125,
|
| 358 |
+
"learning_rate": 1.8e-05,
|
| 359 |
+
"loss": 0.8093,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.1192095885973437,
|
| 364 |
+
"grad_norm": 4.28125,
|
| 365 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 366 |
+
"loss": 0.7798,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.12180110139293812,
|
| 371 |
+
"grad_norm": 4.09375,
|
| 372 |
+
"learning_rate": 1.88e-05,
|
| 373 |
+
"loss": 0.7761,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.12439261418853255,
|
| 378 |
+
"grad_norm": 4.125,
|
| 379 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 380 |
+
"loss": 0.7647,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.12698412698412698,
|
| 385 |
+
"grad_norm": 3.765625,
|
| 386 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 387 |
+
"loss": 0.7612,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.12957563977972142,
|
| 392 |
+
"grad_norm": 4.0,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.7498,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.12957563977972142,
|
| 399 |
+
"eval_loss": 0.744697093963623,
|
| 400 |
+
"eval_model_preparation_time": 0.0003,
|
| 401 |
+
"eval_runtime": 24.6181,
|
| 402 |
+
"eval_samples_per_second": 105.735,
|
| 403 |
+
"eval_steps_per_second": 13.242,
|
| 404 |
+
"step": 50
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.13216715257531583,
|
| 408 |
+
"grad_norm": 4.5,
|
| 409 |
+
"learning_rate": 1.9999560279257315e-05,
|
| 410 |
+
"loss": 0.7504,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.13475866537091027,
|
| 415 |
+
"grad_norm": 3.796875,
|
| 416 |
+
"learning_rate": 1.999824115570012e-05,
|
| 417 |
+
"loss": 0.7181,
|
| 418 |
+
"step": 52
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.1373501781665047,
|
| 422 |
+
"grad_norm": 3.703125,
|
| 423 |
+
"learning_rate": 1.9996042745337617e-05,
|
| 424 |
+
"loss": 0.7195,
|
| 425 |
+
"step": 53
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.13994169096209913,
|
| 429 |
+
"grad_norm": 3.921875,
|
| 430 |
+
"learning_rate": 1.999296524150713e-05,
|
| 431 |
+
"loss": 0.7232,
|
| 432 |
+
"step": 54
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.14253320375769354,
|
| 436 |
+
"grad_norm": 3.6875,
|
| 437 |
+
"learning_rate": 1.9989008914857115e-05,
|
| 438 |
+
"loss": 0.725,
|
| 439 |
+
"step": 55
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.14512471655328799,
|
| 443 |
+
"grad_norm": 3.734375,
|
| 444 |
+
"learning_rate": 1.9984174113323352e-05,
|
| 445 |
+
"loss": 0.6972,
|
| 446 |
+
"step": 56
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.1477162293488824,
|
| 450 |
+
"grad_norm": 3.5,
|
| 451 |
+
"learning_rate": 1.9978461262098342e-05,
|
| 452 |
+
"loss": 0.6792,
|
| 453 |
+
"step": 57
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.15030774214447684,
|
| 457 |
+
"grad_norm": 4.0625,
|
| 458 |
+
"learning_rate": 1.9971870863593924e-05,
|
| 459 |
+
"loss": 0.7192,
|
| 460 |
+
"step": 58
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.15289925494007126,
|
| 464 |
+
"grad_norm": 3.75,
|
| 465 |
+
"learning_rate": 1.9964403497397086e-05,
|
| 466 |
+
"loss": 0.7107,
|
| 467 |
+
"step": 59
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1554907677356657,
|
| 471 |
+
"grad_norm": 3.953125,
|
| 472 |
+
"learning_rate": 1.9956059820218982e-05,
|
| 473 |
+
"loss": 0.6866,
|
| 474 |
+
"step": 60
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.1554907677356657,
|
| 478 |
+
"eval_loss": 0.6849498152732849,
|
| 479 |
+
"eval_model_preparation_time": 0.0003,
|
| 480 |
+
"eval_runtime": 24.5203,
|
| 481 |
+
"eval_samples_per_second": 106.157,
|
| 482 |
+
"eval_steps_per_second": 13.295,
|
| 483 |
+
"step": 60
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.1580822805312601,
|
| 487 |
+
"grad_norm": 3.953125,
|
| 488 |
+
"learning_rate": 1.9946840565837206e-05,
|
| 489 |
+
"loss": 0.6818,
|
| 490 |
+
"step": 61
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.16067379332685455,
|
| 494 |
+
"grad_norm": 3.546875,
|
| 495 |
+
"learning_rate": 1.9936746545031225e-05,
|
| 496 |
+
"loss": 0.6855,
|
| 497 |
+
"step": 62
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.16326530612244897,
|
| 501 |
+
"grad_norm": 3.359375,
|
| 502 |
+
"learning_rate": 1.9925778645511112e-05,
|
| 503 |
+
"loss": 0.6799,
|
| 504 |
+
"step": 63
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.1658568189180434,
|
| 508 |
+
"grad_norm": 3.828125,
|
| 509 |
+
"learning_rate": 1.991393783183945e-05,
|
| 510 |
+
"loss": 0.6719,
|
| 511 |
+
"step": 64
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.16844833171363785,
|
| 515 |
+
"grad_norm": 3.0,
|
| 516 |
+
"learning_rate": 1.990122514534651e-05,
|
| 517 |
+
"loss": 0.66,
|
| 518 |
+
"step": 65
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.17103984450923226,
|
| 522 |
+
"grad_norm": 2.96875,
|
| 523 |
+
"learning_rate": 1.988764170403869e-05,
|
| 524 |
+
"loss": 0.6718,
|
| 525 |
+
"step": 66
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.1736313573048267,
|
| 529 |
+
"grad_norm": 3.15625,
|
| 530 |
+
"learning_rate": 1.9873188702500163e-05,
|
| 531 |
+
"loss": 0.6661,
|
| 532 |
+
"step": 67
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.17622287010042112,
|
| 536 |
+
"grad_norm": 2.828125,
|
| 537 |
+
"learning_rate": 1.9857867411787847e-05,
|
| 538 |
+
"loss": 0.6523,
|
| 539 |
+
"step": 68
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.17881438289601556,
|
| 543 |
+
"grad_norm": 3.203125,
|
| 544 |
+
"learning_rate": 1.9841679179319605e-05,
|
| 545 |
+
"loss": 0.6494,
|
| 546 |
+
"step": 69
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.18140589569160998,
|
| 550 |
+
"grad_norm": 2.875,
|
| 551 |
+
"learning_rate": 1.982462542875576e-05,
|
| 552 |
+
"loss": 0.6411,
|
| 553 |
+
"step": 70
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.18140589569160998,
|
| 557 |
+
"eval_loss": 0.6511064171791077,
|
| 558 |
+
"eval_model_preparation_time": 0.0003,
|
| 559 |
+
"eval_runtime": 24.5304,
|
| 560 |
+
"eval_samples_per_second": 106.113,
|
| 561 |
+
"eval_steps_per_second": 13.29,
|
| 562 |
+
"step": 70
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.18399740848720442,
|
| 566 |
+
"grad_norm": 3.296875,
|
| 567 |
+
"learning_rate": 1.9806707659873886e-05,
|
| 568 |
+
"loss": 0.6463,
|
| 569 |
+
"step": 71
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.18658892128279883,
|
| 573 |
+
"grad_norm": 3.0625,
|
| 574 |
+
"learning_rate": 1.9787927448436913e-05,
|
| 575 |
+
"loss": 0.6375,
|
| 576 |
+
"step": 72
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.18918043407839327,
|
| 580 |
+
"grad_norm": 2.75,
|
| 581 |
+
"learning_rate": 1.9768286446054533e-05,
|
| 582 |
+
"loss": 0.6386,
|
| 583 |
+
"step": 73
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.1917719468739877,
|
| 587 |
+
"grad_norm": 2.875,
|
| 588 |
+
"learning_rate": 1.974778638003799e-05,
|
| 589 |
+
"loss": 0.6368,
|
| 590 |
+
"step": 74
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.19436345966958213,
|
| 594 |
+
"grad_norm": 2.953125,
|
| 595 |
+
"learning_rate": 1.972642905324813e-05,
|
| 596 |
+
"loss": 0.6271,
|
| 597 |
+
"step": 75
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.19695497246517654,
|
| 601 |
+
"grad_norm": 2.921875,
|
| 602 |
+
"learning_rate": 1.9704216343936875e-05,
|
| 603 |
+
"loss": 0.6501,
|
| 604 |
+
"step": 76
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.19954648526077098,
|
| 608 |
+
"grad_norm": 3.015625,
|
| 609 |
+
"learning_rate": 1.9681150205582025e-05,
|
| 610 |
+
"loss": 0.6111,
|
| 611 |
+
"step": 77
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2021379980563654,
|
| 615 |
+
"grad_norm": 3.171875,
|
| 616 |
+
"learning_rate": 1.9657232666715485e-05,
|
| 617 |
+
"loss": 0.651,
|
| 618 |
+
"step": 78
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.20472951085195984,
|
| 622 |
+
"grad_norm": 3.0625,
|
| 623 |
+
"learning_rate": 1.9632465830744846e-05,
|
| 624 |
+
"loss": 0.6184,
|
| 625 |
+
"step": 79
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.20732102364755425,
|
| 629 |
+
"grad_norm": 3.25,
|
| 630 |
+
"learning_rate": 1.9606851875768404e-05,
|
| 631 |
+
"loss": 0.6259,
|
| 632 |
+
"step": 80
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20732102364755425,
|
| 636 |
+
"eval_loss": 0.6278263330459595,
|
| 637 |
+
"eval_model_preparation_time": 0.0003,
|
| 638 |
+
"eval_runtime": 24.4892,
|
| 639 |
+
"eval_samples_per_second": 106.292,
|
| 640 |
+
"eval_steps_per_second": 13.312,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2099125364431487,
|
| 645 |
+
"grad_norm": 2.875,
|
| 646 |
+
"learning_rate": 1.9580393054383622e-05,
|
| 647 |
+
"loss": 0.6288,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2125040492387431,
|
| 652 |
+
"grad_norm": 3.359375,
|
| 653 |
+
"learning_rate": 1.9553091693489018e-05,
|
| 654 |
+
"loss": 0.6403,
|
| 655 |
+
"step": 82
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.21509556203433755,
|
| 659 |
+
"grad_norm": 2.921875,
|
| 660 |
+
"learning_rate": 1.9524950194079534e-05,
|
| 661 |
+
"loss": 0.621,
|
| 662 |
+
"step": 83
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.21768707482993196,
|
| 666 |
+
"grad_norm": 2.84375,
|
| 667 |
+
"learning_rate": 1.9495971031035367e-05,
|
| 668 |
+
"loss": 0.6135,
|
| 669 |
+
"step": 84
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.2202785876255264,
|
| 673 |
+
"grad_norm": 2.921875,
|
| 674 |
+
"learning_rate": 1.9466156752904344e-05,
|
| 675 |
+
"loss": 0.6211,
|
| 676 |
+
"step": 85
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.22287010042112082,
|
| 680 |
+
"grad_norm": 3.109375,
|
| 681 |
+
"learning_rate": 1.9435509981677764e-05,
|
| 682 |
+
"loss": 0.6198,
|
| 683 |
+
"step": 86
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.22546161321671526,
|
| 687 |
+
"grad_norm": 2.625,
|
| 688 |
+
"learning_rate": 1.9404033412559828e-05,
|
| 689 |
+
"loss": 0.5972,
|
| 690 |
+
"step": 87
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.22805312601230968,
|
| 694 |
+
"grad_norm": 3.0,
|
| 695 |
+
"learning_rate": 1.9371729813730606e-05,
|
| 696 |
+
"loss": 0.614,
|
| 697 |
+
"step": 88
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.23064463880790412,
|
| 701 |
+
"grad_norm": 2.75,
|
| 702 |
+
"learning_rate": 1.9338602026102594e-05,
|
| 703 |
+
"loss": 0.5998,
|
| 704 |
+
"step": 89
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.23323615160349853,
|
| 708 |
+
"grad_norm": 2.796875,
|
| 709 |
+
"learning_rate": 1.9304652963070868e-05,
|
| 710 |
+
"loss": 0.6181,
|
| 711 |
+
"step": 90
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.23323615160349853,
|
| 715 |
+
"eval_loss": 0.6108965277671814,
|
| 716 |
+
"eval_model_preparation_time": 0.0003,
|
| 717 |
+
"eval_runtime": 24.4982,
|
| 718 |
+
"eval_samples_per_second": 106.253,
|
| 719 |
+
"eval_steps_per_second": 13.307,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.23582766439909297,
|
| 724 |
+
"grad_norm": 2.8125,
|
| 725 |
+
"learning_rate": 1.9269885610256866e-05,
|
| 726 |
+
"loss": 0.6059,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2384191771946874,
|
| 731 |
+
"grad_norm": 2.734375,
|
| 732 |
+
"learning_rate": 1.9234303025245835e-05,
|
| 733 |
+
"loss": 0.6165,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.24101068999028183,
|
| 738 |
+
"grad_norm": 2.984375,
|
| 739 |
+
"learning_rate": 1.919790833731791e-05,
|
| 740 |
+
"loss": 0.6241,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.24360220278587624,
|
| 745 |
+
"grad_norm": 3.015625,
|
| 746 |
+
"learning_rate": 1.9160704747172935e-05,
|
| 747 |
+
"loss": 0.5913,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.24619371558147068,
|
| 752 |
+
"grad_norm": 2.84375,
|
| 753 |
+
"learning_rate": 1.9122695526648968e-05,
|
| 754 |
+
"loss": 0.585,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.2487852283770651,
|
| 759 |
+
"grad_norm": 3.484375,
|
| 760 |
+
"learning_rate": 1.9083884018434545e-05,
|
| 761 |
+
"loss": 0.5897,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.2513767411726595,
|
| 766 |
+
"grad_norm": 2.84375,
|
| 767 |
+
"learning_rate": 1.9044273635774707e-05,
|
| 768 |
+
"loss": 0.6032,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.25396825396825395,
|
| 773 |
+
"grad_norm": 2.75,
|
| 774 |
+
"learning_rate": 1.900386786217083e-05,
|
| 775 |
+
"loss": 0.594,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.2565597667638484,
|
| 780 |
+
"grad_norm": 2.8125,
|
| 781 |
+
"learning_rate": 1.8962670251074276e-05,
|
| 782 |
+
"loss": 0.5958,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.25915127955944284,
|
| 787 |
+
"grad_norm": 2.65625,
|
| 788 |
+
"learning_rate": 1.8920684425573865e-05,
|
| 789 |
+
"loss": 0.5821,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.25915127955944284,
|
| 794 |
+
"eval_loss": 0.5988509058952332,
|
| 795 |
+
"eval_model_preparation_time": 0.0003,
|
| 796 |
+
"eval_runtime": 24.4884,
|
| 797 |
+
"eval_samples_per_second": 106.295,
|
| 798 |
+
"eval_steps_per_second": 13.312,
|
| 799 |
+
"step": 100
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.2617427923550373,
|
| 803 |
+
"grad_norm": 2.65625,
|
| 804 |
+
"learning_rate": 1.887791407807728e-05,
|
| 805 |
+
"loss": 0.5904,
|
| 806 |
+
"step": 101
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.26433430515063167,
|
| 810 |
+
"grad_norm": 2.359375,
|
| 811 |
+
"learning_rate": 1.883436296998631e-05,
|
| 812 |
+
"loss": 0.5913,
|
| 813 |
+
"step": 102
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.2669258179462261,
|
| 817 |
+
"grad_norm": 2.46875,
|
| 818 |
+
"learning_rate": 1.8790034931366073e-05,
|
| 819 |
+
"loss": 0.6114,
|
| 820 |
+
"step": 103
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.26951733074182055,
|
| 824 |
+
"grad_norm": 2.359375,
|
| 825 |
+
"learning_rate": 1.8744933860608183e-05,
|
| 826 |
+
"loss": 0.5803,
|
| 827 |
+
"step": 104
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.272108843537415,
|
| 831 |
+
"grad_norm": 3.40625,
|
| 832 |
+
"learning_rate": 1.8699063724087905e-05,
|
| 833 |
+
"loss": 0.5865,
|
| 834 |
+
"step": 105
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.2747003563330094,
|
| 838 |
+
"grad_norm": 2.28125,
|
| 839 |
+
"learning_rate": 1.865242855581534e-05,
|
| 840 |
+
"loss": 0.586,
|
| 841 |
+
"step": 106
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.2772918691286038,
|
| 845 |
+
"grad_norm": 2.453125,
|
| 846 |
+
"learning_rate": 1.8605032457080655e-05,
|
| 847 |
+
"loss": 0.5926,
|
| 848 |
+
"step": 107
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.27988338192419826,
|
| 852 |
+
"grad_norm": 2.203125,
|
| 853 |
+
"learning_rate": 1.8556879596093393e-05,
|
| 854 |
+
"loss": 0.5927,
|
| 855 |
+
"step": 108
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.2824748947197927,
|
| 859 |
+
"grad_norm": 2.890625,
|
| 860 |
+
"learning_rate": 1.850797420761592e-05,
|
| 861 |
+
"loss": 0.5937,
|
| 862 |
+
"step": 109
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.2850664075153871,
|
| 866 |
+
"grad_norm": 2.390625,
|
| 867 |
+
"learning_rate": 1.8458320592590976e-05,
|
| 868 |
+
"loss": 0.5644,
|
| 869 |
+
"step": 110
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.2850664075153871,
|
| 873 |
+
"eval_loss": 0.5878391265869141,
|
| 874 |
+
"eval_model_preparation_time": 0.0003,
|
| 875 |
+
"eval_runtime": 24.539,
|
| 876 |
+
"eval_samples_per_second": 106.076,
|
| 877 |
+
"eval_steps_per_second": 13.285,
|
| 878 |
+
"step": 110
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.28765792031098153,
|
| 882 |
+
"grad_norm": 2.75,
|
| 883 |
+
"learning_rate": 1.840792311776346e-05,
|
| 884 |
+
"loss": 0.5783,
|
| 885 |
+
"step": 111
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.29024943310657597,
|
| 889 |
+
"grad_norm": 2.375,
|
| 890 |
+
"learning_rate": 1.8356786215296387e-05,
|
| 891 |
+
"loss": 0.5813,
|
| 892 |
+
"step": 112
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.2928409459021704,
|
| 896 |
+
"grad_norm": 2.46875,
|
| 897 |
+
"learning_rate": 1.83049143823811e-05,
|
| 898 |
+
"loss": 0.5788,
|
| 899 |
+
"step": 113
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.2954324586977648,
|
| 903 |
+
"grad_norm": 2.71875,
|
| 904 |
+
"learning_rate": 1.825231218084178e-05,
|
| 905 |
+
"loss": 0.5831,
|
| 906 |
+
"step": 114
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.29802397149335924,
|
| 910 |
+
"grad_norm": 2.484375,
|
| 911 |
+
"learning_rate": 1.8198984236734246e-05,
|
| 912 |
+
"loss": 0.5715,
|
| 913 |
+
"step": 115
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.3006154842889537,
|
| 917 |
+
"grad_norm": 2.546875,
|
| 918 |
+
"learning_rate": 1.8144935239939147e-05,
|
| 919 |
+
"loss": 0.5938,
|
| 920 |
+
"step": 116
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.3032069970845481,
|
| 924 |
+
"grad_norm": 2.90625,
|
| 925 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 926 |
+
"loss": 0.5911,
|
| 927 |
+
"step": 117
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.3057985098801425,
|
| 931 |
+
"grad_norm": 2.859375,
|
| 932 |
+
"learning_rate": 1.8034693164452578e-05,
|
| 933 |
+
"loss": 0.5815,
|
| 934 |
+
"step": 118
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.30839002267573695,
|
| 938 |
+
"grad_norm": 2.65625,
|
| 939 |
+
"learning_rate": 1.7978509780906578e-05,
|
| 940 |
+
"loss": 0.5804,
|
| 941 |
+
"step": 119
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.3109815354713314,
|
| 945 |
+
"grad_norm": 2.828125,
|
| 946 |
+
"learning_rate": 1.7921624734111292e-05,
|
| 947 |
+
"loss": 0.5749,
|
| 948 |
+
"step": 120
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.3109815354713314,
|
| 952 |
+
"eval_loss": 0.5794549584388733,
|
| 953 |
+
"eval_model_preparation_time": 0.0003,
|
| 954 |
+
"eval_runtime": 24.5897,
|
| 955 |
+
"eval_samples_per_second": 105.857,
|
| 956 |
+
"eval_steps_per_second": 13.258,
|
| 957 |
+
"step": 120
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.31357304826692584,
|
| 961 |
+
"grad_norm": 2.703125,
|
| 962 |
+
"learning_rate": 1.786404302677374e-05,
|
| 963 |
+
"loss": 0.5873,
|
| 964 |
+
"step": 121
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.3161645610625202,
|
| 968 |
+
"grad_norm": 2.375,
|
| 969 |
+
"learning_rate": 1.7805769722868132e-05,
|
| 970 |
+
"loss": 0.5856,
|
| 971 |
+
"step": 122
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.31875607385811466,
|
| 975 |
+
"grad_norm": 2.984375,
|
| 976 |
+
"learning_rate": 1.7746809947190567e-05,
|
| 977 |
+
"loss": 0.578,
|
| 978 |
+
"step": 123
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.3213475866537091,
|
| 982 |
+
"grad_norm": 3.421875,
|
| 983 |
+
"learning_rate": 1.768716888490832e-05,
|
| 984 |
+
"loss": 0.5566,
|
| 985 |
+
"step": 124
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.32393909944930355,
|
| 989 |
+
"grad_norm": 2.5625,
|
| 990 |
+
"learning_rate": 1.762685178110382e-05,
|
| 991 |
+
"loss": 0.5638,
|
| 992 |
+
"step": 125
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.32653061224489793,
|
| 996 |
+
"grad_norm": 3.125,
|
| 997 |
+
"learning_rate": 1.7565863940313416e-05,
|
| 998 |
+
"loss": 0.5827,
|
| 999 |
+
"step": 126
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.3291221250404924,
|
| 1003 |
+
"grad_norm": 3.1875,
|
| 1004 |
+
"learning_rate": 1.7504210726060828e-05,
|
| 1005 |
+
"loss": 0.5596,
|
| 1006 |
+
"step": 127
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.3317136378360868,
|
| 1010 |
+
"grad_norm": 2.984375,
|
| 1011 |
+
"learning_rate": 1.7441897560385493e-05,
|
| 1012 |
+
"loss": 0.5768,
|
| 1013 |
+
"step": 128
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.33430515063168126,
|
| 1017 |
+
"grad_norm": 2.546875,
|
| 1018 |
+
"learning_rate": 1.7378929923365706e-05,
|
| 1019 |
+
"loss": 0.5732,
|
| 1020 |
+
"step": 129
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.3368966634272757,
|
| 1024 |
+
"grad_norm": 2.78125,
|
| 1025 |
+
"learning_rate": 1.731531335263669e-05,
|
| 1026 |
+
"loss": 0.5781,
|
| 1027 |
+
"step": 130
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.3368966634272757,
|
| 1031 |
+
"eval_loss": 0.572753369808197,
|
| 1032 |
+
"eval_model_preparation_time": 0.0003,
|
| 1033 |
+
"eval_runtime": 24.5459,
|
| 1034 |
+
"eval_samples_per_second": 106.046,
|
| 1035 |
+
"eval_steps_per_second": 13.281,
|
| 1036 |
+
"step": 130
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.3394881762228701,
|
| 1040 |
+
"grad_norm": 2.421875,
|
| 1041 |
+
"learning_rate": 1.7251053442903597e-05,
|
| 1042 |
+
"loss": 0.5689,
|
| 1043 |
+
"step": 131
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.34207968901846453,
|
| 1047 |
+
"grad_norm": 3.546875,
|
| 1048 |
+
"learning_rate": 1.7186155845449465e-05,
|
| 1049 |
+
"loss": 0.5695,
|
| 1050 |
+
"step": 132
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.34467120181405897,
|
| 1054 |
+
"grad_norm": 2.4375,
|
| 1055 |
+
"learning_rate": 1.712062626763825e-05,
|
| 1056 |
+
"loss": 0.5627,
|
| 1057 |
+
"step": 133
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.3472627146096534,
|
| 1061 |
+
"grad_norm": 2.796875,
|
| 1062 |
+
"learning_rate": 1.7054470472412876e-05,
|
| 1063 |
+
"loss": 0.5759,
|
| 1064 |
+
"step": 134
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.3498542274052478,
|
| 1068 |
+
"grad_norm": 2.4375,
|
| 1069 |
+
"learning_rate": 1.698769427778842e-05,
|
| 1070 |
+
"loss": 0.5662,
|
| 1071 |
+
"step": 135
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.35244574020084224,
|
| 1075 |
+
"grad_norm": 2.40625,
|
| 1076 |
+
"learning_rate": 1.6920303556340462e-05,
|
| 1077 |
+
"loss": 0.5671,
|
| 1078 |
+
"step": 136
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.3550372529964367,
|
| 1082 |
+
"grad_norm": 2.890625,
|
| 1083 |
+
"learning_rate": 1.6852304234688627e-05,
|
| 1084 |
+
"loss": 0.5572,
|
| 1085 |
+
"step": 137
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.3576287657920311,
|
| 1089 |
+
"grad_norm": 2.890625,
|
| 1090 |
+
"learning_rate": 1.678370229297535e-05,
|
| 1091 |
+
"loss": 0.5796,
|
| 1092 |
+
"step": 138
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.3602202785876255,
|
| 1096 |
+
"grad_norm": 3.03125,
|
| 1097 |
+
"learning_rate": 1.6714503764339986e-05,
|
| 1098 |
+
"loss": 0.5642,
|
| 1099 |
+
"step": 139
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.36281179138321995,
|
| 1103 |
+
"grad_norm": 2.3125,
|
| 1104 |
+
"learning_rate": 1.664471473438822e-05,
|
| 1105 |
+
"loss": 0.5711,
|
| 1106 |
+
"step": 140
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.36281179138321995,
|
| 1110 |
+
"eval_loss": 0.566669762134552,
|
| 1111 |
+
"eval_model_preparation_time": 0.0003,
|
| 1112 |
+
"eval_runtime": 24.5724,
|
| 1113 |
+
"eval_samples_per_second": 105.932,
|
| 1114 |
+
"eval_steps_per_second": 13.267,
|
| 1115 |
+
"step": 140
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3654033041788144,
|
| 1119 |
+
"grad_norm": 2.625,
|
| 1120 |
+
"learning_rate": 1.657434134065686e-05,
|
| 1121 |
+
"loss": 0.5559,
|
| 1122 |
+
"step": 141
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.36799481697440883,
|
| 1126 |
+
"grad_norm": 3.015625,
|
| 1127 |
+
"learning_rate": 1.6503389772074104e-05,
|
| 1128 |
+
"loss": 0.575,
|
| 1129 |
+
"step": 142
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.3705863297700032,
|
| 1133 |
+
"grad_norm": 2.984375,
|
| 1134 |
+
"learning_rate": 1.643186626841524e-05,
|
| 1135 |
+
"loss": 0.5851,
|
| 1136 |
+
"step": 143
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.37317784256559766,
|
| 1140 |
+
"grad_norm": 2.609375,
|
| 1141 |
+
"learning_rate": 1.6359777119753887e-05,
|
| 1142 |
+
"loss": 0.559,
|
| 1143 |
+
"step": 144
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.3757693553611921,
|
| 1147 |
+
"grad_norm": 2.40625,
|
| 1148 |
+
"learning_rate": 1.628712866590885e-05,
|
| 1149 |
+
"loss": 0.5759,
|
| 1150 |
+
"step": 145
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.37836086815678655,
|
| 1154 |
+
"grad_norm": 2.328125,
|
| 1155 |
+
"learning_rate": 1.6213927295886547e-05,
|
| 1156 |
+
"loss": 0.5579,
|
| 1157 |
+
"step": 146
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.38095238095238093,
|
| 1161 |
+
"grad_norm": 2.453125,
|
| 1162 |
+
"learning_rate": 1.6140179447319134e-05,
|
| 1163 |
+
"loss": 0.5717,
|
| 1164 |
+
"step": 147
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.3835438937479754,
|
| 1168 |
+
"grad_norm": 2.4375,
|
| 1169 |
+
"learning_rate": 1.6065891605898358e-05,
|
| 1170 |
+
"loss": 0.5531,
|
| 1171 |
+
"step": 148
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.3861354065435698,
|
| 1175 |
+
"grad_norm": 2.484375,
|
| 1176 |
+
"learning_rate": 1.5991070304805184e-05,
|
| 1177 |
+
"loss": 0.5358,
|
| 1178 |
+
"step": 149
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.38872691933916426,
|
| 1182 |
+
"grad_norm": 2.46875,
|
| 1183 |
+
"learning_rate": 1.5915722124135227e-05,
|
| 1184 |
+
"loss": 0.5715,
|
| 1185 |
+
"step": 150
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.38872691933916426,
|
| 1189 |
+
"eval_loss": 0.5618191361427307,
|
| 1190 |
+
"eval_model_preparation_time": 0.0003,
|
| 1191 |
+
"eval_runtime": 24.5943,
|
| 1192 |
+
"eval_samples_per_second": 105.838,
|
| 1193 |
+
"eval_steps_per_second": 13.255,
|
| 1194 |
+
"step": 150
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.39131843213475864,
|
| 1198 |
+
"grad_norm": 2.390625,
|
| 1199 |
+
"learning_rate": 1.5839853690320074e-05,
|
| 1200 |
+
"loss": 0.5413,
|
| 1201 |
+
"step": 151
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.3939099449303531,
|
| 1205 |
+
"grad_norm": 2.28125,
|
| 1206 |
+
"learning_rate": 1.5763471675544547e-05,
|
| 1207 |
+
"loss": 0.5652,
|
| 1208 |
+
"step": 152
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.3965014577259475,
|
| 1212 |
+
"grad_norm": 2.609375,
|
| 1213 |
+
"learning_rate": 1.5686582797159892e-05,
|
| 1214 |
+
"loss": 0.5682,
|
| 1215 |
+
"step": 153
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.39909297052154197,
|
| 1219 |
+
"grad_norm": 2.71875,
|
| 1220 |
+
"learning_rate": 1.5609193817093057e-05,
|
| 1221 |
+
"loss": 0.5577,
|
| 1222 |
+
"step": 154
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.40168448331713635,
|
| 1226 |
+
"grad_norm": 2.65625,
|
| 1227 |
+
"learning_rate": 1.5531311541251995e-05,
|
| 1228 |
+
"loss": 0.5412,
|
| 1229 |
+
"step": 155
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.4042759961127308,
|
| 1233 |
+
"grad_norm": 2.4375,
|
| 1234 |
+
"learning_rate": 1.5452942818927144e-05,
|
| 1235 |
+
"loss": 0.5441,
|
| 1236 |
+
"step": 156
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.40686750890832524,
|
| 1240 |
+
"grad_norm": 2.390625,
|
| 1241 |
+
"learning_rate": 1.5374094542189055e-05,
|
| 1242 |
+
"loss": 0.5764,
|
| 1243 |
+
"step": 157
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.4094590217039197,
|
| 1247 |
+
"grad_norm": 3.078125,
|
| 1248 |
+
"learning_rate": 1.52947736452823e-05,
|
| 1249 |
+
"loss": 0.5763,
|
| 1250 |
+
"step": 158
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.41205053449951407,
|
| 1254 |
+
"grad_norm": 2.5625,
|
| 1255 |
+
"learning_rate": 1.521498710401561e-05,
|
| 1256 |
+
"loss": 0.5482,
|
| 1257 |
+
"step": 159
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.4146420472951085,
|
| 1261 |
+
"grad_norm": 2.375,
|
| 1262 |
+
"learning_rate": 1.513474193514842e-05,
|
| 1263 |
+
"loss": 0.559,
|
| 1264 |
+
"step": 160
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.4146420472951085,
|
| 1268 |
+
"eval_loss": 0.5573883056640625,
|
| 1269 |
+
"eval_model_preparation_time": 0.0003,
|
| 1270 |
+
"eval_runtime": 24.5874,
|
| 1271 |
+
"eval_samples_per_second": 105.867,
|
| 1272 |
+
"eval_steps_per_second": 13.259,
|
| 1273 |
+
"step": 160
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.41723356009070295,
|
| 1277 |
+
"grad_norm": 2.28125,
|
| 1278 |
+
"learning_rate": 1.505404519577379e-05,
|
| 1279 |
+
"loss": 0.5642,
|
| 1280 |
+
"step": 161
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.4198250728862974,
|
| 1284 |
+
"grad_norm": 2.40625,
|
| 1285 |
+
"learning_rate": 1.4972903982697744e-05,
|
| 1286 |
+
"loss": 0.5535,
|
| 1287 |
+
"step": 162
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.42241658568189183,
|
| 1291 |
+
"grad_norm": 2.34375,
|
| 1292 |
+
"learning_rate": 1.4891325431815182e-05,
|
| 1293 |
+
"loss": 0.5519,
|
| 1294 |
+
"step": 163
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.4250080984774862,
|
| 1298 |
+
"grad_norm": 2.0,
|
| 1299 |
+
"learning_rate": 1.48093167174823e-05,
|
| 1300 |
+
"loss": 0.5611,
|
| 1301 |
+
"step": 164
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.42759961127308066,
|
| 1305 |
+
"grad_norm": 2.140625,
|
| 1306 |
+
"learning_rate": 1.4726885051885654e-05,
|
| 1307 |
+
"loss": 0.5556,
|
| 1308 |
+
"step": 165
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.4301911240686751,
|
| 1312 |
+
"grad_norm": 2.40625,
|
| 1313 |
+
"learning_rate": 1.4644037684407883e-05,
|
| 1314 |
+
"loss": 0.5289,
|
| 1315 |
+
"step": 166
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.43278263686426954,
|
| 1319 |
+
"grad_norm": 2.09375,
|
| 1320 |
+
"learning_rate": 1.4560781900990187e-05,
|
| 1321 |
+
"loss": 0.5538,
|
| 1322 |
+
"step": 167
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.43537414965986393,
|
| 1326 |
+
"grad_norm": 2.34375,
|
| 1327 |
+
"learning_rate": 1.4477125023491536e-05,
|
| 1328 |
+
"loss": 0.5589,
|
| 1329 |
+
"step": 168
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.43796566245545837,
|
| 1333 |
+
"grad_norm": 2.359375,
|
| 1334 |
+
"learning_rate": 1.4393074409044802e-05,
|
| 1335 |
+
"loss": 0.5423,
|
| 1336 |
+
"step": 169
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.4405571752510528,
|
| 1340 |
+
"grad_norm": 2.15625,
|
| 1341 |
+
"learning_rate": 1.4308637449409705e-05,
|
| 1342 |
+
"loss": 0.5593,
|
| 1343 |
+
"step": 170
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.4405571752510528,
|
| 1347 |
+
"eval_loss": 0.553532063961029,
|
| 1348 |
+
"eval_model_preparation_time": 0.0003,
|
| 1349 |
+
"eval_runtime": 24.5188,
|
| 1350 |
+
"eval_samples_per_second": 106.163,
|
| 1351 |
+
"eval_steps_per_second": 13.296,
|
| 1352 |
+
"step": 170
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.44314868804664725,
|
| 1356 |
+
"grad_norm": 2.421875,
|
| 1357 |
+
"learning_rate": 1.4223821570322762e-05,
|
| 1358 |
+
"loss": 0.5789,
|
| 1359 |
+
"step": 171
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.44574020084224164,
|
| 1363 |
+
"grad_norm": 2.4375,
|
| 1364 |
+
"learning_rate": 1.4138634230844242e-05,
|
| 1365 |
+
"loss": 0.5693,
|
| 1366 |
+
"step": 172
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.4483317136378361,
|
| 1370 |
+
"grad_norm": 2.296875,
|
| 1371 |
+
"learning_rate": 1.4053082922702183e-05,
|
| 1372 |
+
"loss": 0.5496,
|
| 1373 |
+
"step": 173
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.4509232264334305,
|
| 1377 |
+
"grad_norm": 2.21875,
|
| 1378 |
+
"learning_rate": 1.3967175169633537e-05,
|
| 1379 |
+
"loss": 0.5362,
|
| 1380 |
+
"step": 174
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.45351473922902497,
|
| 1384 |
+
"grad_norm": 2.1875,
|
| 1385 |
+
"learning_rate": 1.3880918526722497e-05,
|
| 1386 |
+
"loss": 0.5739,
|
| 1387 |
+
"step": 175
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.45610625202461935,
|
| 1391 |
+
"grad_norm": 2.421875,
|
| 1392 |
+
"learning_rate": 1.3794320579736084e-05,
|
| 1393 |
+
"loss": 0.5493,
|
| 1394 |
+
"step": 176
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.4586977648202138,
|
| 1398 |
+
"grad_norm": 2.59375,
|
| 1399 |
+
"learning_rate": 1.3707388944457007e-05,
|
| 1400 |
+
"loss": 0.5665,
|
| 1401 |
+
"step": 177
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.46128927761580824,
|
| 1405 |
+
"grad_norm": 2.125,
|
| 1406 |
+
"learning_rate": 1.3620131266013912e-05,
|
| 1407 |
+
"loss": 0.5557,
|
| 1408 |
+
"step": 178
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.4638807904114027,
|
| 1412 |
+
"grad_norm": 2.34375,
|
| 1413 |
+
"learning_rate": 1.3532555218209037e-05,
|
| 1414 |
+
"loss": 0.5402,
|
| 1415 |
+
"step": 179
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.46647230320699706,
|
| 1419 |
+
"grad_norm": 2.375,
|
| 1420 |
+
"learning_rate": 1.344466850284333e-05,
|
| 1421 |
+
"loss": 0.5625,
|
| 1422 |
+
"step": 180
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.46647230320699706,
|
| 1426 |
+
"eval_loss": 0.5502737164497375,
|
| 1427 |
+
"eval_model_preparation_time": 0.0003,
|
| 1428 |
+
"eval_runtime": 24.6233,
|
| 1429 |
+
"eval_samples_per_second": 105.713,
|
| 1430 |
+
"eval_steps_per_second": 13.239,
|
| 1431 |
+
"step": 180
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.4690638160025915,
|
| 1435 |
+
"grad_norm": 2.34375,
|
| 1436 |
+
"learning_rate": 1.335647884903915e-05,
|
| 1437 |
+
"loss": 0.5492,
|
| 1438 |
+
"step": 181
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.47165532879818595,
|
| 1442 |
+
"grad_norm": 2.390625,
|
| 1443 |
+
"learning_rate": 1.3267994012560505e-05,
|
| 1444 |
+
"loss": 0.5493,
|
| 1445 |
+
"step": 182
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.4742468415937804,
|
| 1449 |
+
"grad_norm": 2.453125,
|
| 1450 |
+
"learning_rate": 1.3179221775131005e-05,
|
| 1451 |
+
"loss": 0.5508,
|
| 1452 |
+
"step": 183
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.4768383543893748,
|
| 1456 |
+
"grad_norm": 3.34375,
|
| 1457 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 1458 |
+
"loss": 0.5427,
|
| 1459 |
+
"step": 184
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.4794298671849692,
|
| 1463 |
+
"grad_norm": 2.078125,
|
| 1464 |
+
"learning_rate": 1.300084635000341e-05,
|
| 1465 |
+
"loss": 0.568,
|
| 1466 |
+
"step": 185
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.48202137998056366,
|
| 1470 |
+
"grad_norm": 2.15625,
|
| 1471 |
+
"learning_rate": 1.2911258849380199e-05,
|
| 1472 |
+
"loss": 0.5478,
|
| 1473 |
+
"step": 186
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.4846128927761581,
|
| 1477 |
+
"grad_norm": 2.15625,
|
| 1478 |
+
"learning_rate": 1.2821415320576309e-05,
|
| 1479 |
+
"loss": 0.5582,
|
| 1480 |
+
"step": 187
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.4872044055717525,
|
| 1484 |
+
"grad_norm": 3.0,
|
| 1485 |
+
"learning_rate": 1.273132366480438e-05,
|
| 1486 |
+
"loss": 0.5368,
|
| 1487 |
+
"step": 188
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.4897959183673469,
|
| 1491 |
+
"grad_norm": 2.71875,
|
| 1492 |
+
"learning_rate": 1.2640991805098369e-05,
|
| 1493 |
+
"loss": 0.5608,
|
| 1494 |
+
"step": 189
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.49238743116294137,
|
| 1498 |
+
"grad_norm": 2.203125,
|
| 1499 |
+
"learning_rate": 1.2550427685616767e-05,
|
| 1500 |
+
"loss": 0.5482,
|
| 1501 |
+
"step": 190
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.49238743116294137,
|
| 1505 |
+
"eval_loss": 0.547302782535553,
|
| 1506 |
+
"eval_model_preparation_time": 0.0003,
|
| 1507 |
+
"eval_runtime": 24.5429,
|
| 1508 |
+
"eval_samples_per_second": 106.059,
|
| 1509 |
+
"eval_steps_per_second": 13.283,
|
| 1510 |
+
"step": 190
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.4949789439585358,
|
| 1514 |
+
"grad_norm": 2.640625,
|
| 1515 |
+
"learning_rate": 1.2459639270943944e-05,
|
| 1516 |
+
"loss": 0.5508,
|
| 1517 |
+
"step": 191
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.4975704567541302,
|
| 1521 |
+
"grad_norm": 2.65625,
|
| 1522 |
+
"learning_rate": 1.2368634545389732e-05,
|
| 1523 |
+
"loss": 0.5402,
|
| 1524 |
+
"step": 192
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.5001619695497247,
|
| 1528 |
+
"grad_norm": 2.25,
|
| 1529 |
+
"learning_rate": 1.2277421512287227e-05,
|
| 1530 |
+
"loss": 0.5313,
|
| 1531 |
+
"step": 193
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.502753482345319,
|
| 1535 |
+
"grad_norm": 2.296875,
|
| 1536 |
+
"learning_rate": 1.2186008193288963e-05,
|
| 1537 |
+
"loss": 0.5535,
|
| 1538 |
+
"step": 194
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.5053449951409135,
|
| 1542 |
+
"grad_norm": 2.234375,
|
| 1543 |
+
"learning_rate": 1.2094402627661447e-05,
|
| 1544 |
+
"loss": 0.5375,
|
| 1545 |
+
"step": 195
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.5079365079365079,
|
| 1549 |
+
"grad_norm": 2.375,
|
| 1550 |
+
"learning_rate": 1.2002612871578143e-05,
|
| 1551 |
+
"loss": 0.5564,
|
| 1552 |
+
"step": 196
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.5105280207321024,
|
| 1556 |
+
"grad_norm": 2.5,
|
| 1557 |
+
"learning_rate": 1.1910646997411002e-05,
|
| 1558 |
+
"loss": 0.5459,
|
| 1559 |
+
"step": 197
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.5131195335276968,
|
| 1563 |
+
"grad_norm": 2.3125,
|
| 1564 |
+
"learning_rate": 1.1818513093020514e-05,
|
| 1565 |
+
"loss": 0.5545,
|
| 1566 |
+
"step": 198
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.5157110463232912,
|
| 1570 |
+
"grad_norm": 2.21875,
|
| 1571 |
+
"learning_rate": 1.172621926104446e-05,
|
| 1572 |
+
"loss": 0.535,
|
| 1573 |
+
"step": 199
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.5183025591188857,
|
| 1577 |
+
"grad_norm": 2.234375,
|
| 1578 |
+
"learning_rate": 1.1633773618185302e-05,
|
| 1579 |
+
"loss": 0.5469,
|
| 1580 |
+
"step": 200
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.5183025591188857,
|
| 1584 |
+
"eval_loss": 0.545219898223877,
|
| 1585 |
+
"eval_model_preparation_time": 0.0003,
|
| 1586 |
+
"eval_runtime": 24.4828,
|
| 1587 |
+
"eval_samples_per_second": 106.319,
|
| 1588 |
+
"eval_steps_per_second": 13.315,
|
| 1589 |
+
"step": 200
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.5208940719144801,
|
| 1593 |
+
"grad_norm": 2.203125,
|
| 1594 |
+
"learning_rate": 1.1541184294496393e-05,
|
| 1595 |
+
"loss": 0.5349,
|
| 1596 |
+
"step": 201
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.5234855847100746,
|
| 1600 |
+
"grad_norm": 2.46875,
|
| 1601 |
+
"learning_rate": 1.144845943266696e-05,
|
| 1602 |
+
"loss": 0.5271,
|
| 1603 |
+
"step": 202
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.5260770975056689,
|
| 1607 |
+
"grad_norm": 2.28125,
|
| 1608 |
+
"learning_rate": 1.1355607187306036e-05,
|
| 1609 |
+
"loss": 0.5431,
|
| 1610 |
+
"step": 203
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.5286686103012633,
|
| 1614 |
+
"grad_norm": 2.34375,
|
| 1615 |
+
"learning_rate": 1.1262635724225273e-05,
|
| 1616 |
+
"loss": 0.5344,
|
| 1617 |
+
"step": 204
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.5312601230968578,
|
| 1621 |
+
"grad_norm": 2.53125,
|
| 1622 |
+
"learning_rate": 1.1169553219720828e-05,
|
| 1623 |
+
"loss": 0.5386,
|
| 1624 |
+
"step": 205
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.5338516358924522,
|
| 1628 |
+
"grad_norm": 2.34375,
|
| 1629 |
+
"learning_rate": 1.1076367859854305e-05,
|
| 1630 |
+
"loss": 0.5277,
|
| 1631 |
+
"step": 206
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.5364431486880467,
|
| 1635 |
+
"grad_norm": 2.328125,
|
| 1636 |
+
"learning_rate": 1.0983087839732834e-05,
|
| 1637 |
+
"loss": 0.5339,
|
| 1638 |
+
"step": 207
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.5390346614836411,
|
| 1642 |
+
"grad_norm": 2.4375,
|
| 1643 |
+
"learning_rate": 1.0889721362788361e-05,
|
| 1644 |
+
"loss": 0.5535,
|
| 1645 |
+
"step": 208
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.5416261742792355,
|
| 1649 |
+
"grad_norm": 2.28125,
|
| 1650 |
+
"learning_rate": 1.0796276640056201e-05,
|
| 1651 |
+
"loss": 0.5385,
|
| 1652 |
+
"step": 209
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.54421768707483,
|
| 1656 |
+
"grad_norm": 2.3125,
|
| 1657 |
+
"learning_rate": 1.070276188945293e-05,
|
| 1658 |
+
"loss": 0.5628,
|
| 1659 |
+
"step": 210
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.54421768707483,
|
| 1663 |
+
"eval_loss": 0.5431892275810242,
|
| 1664 |
+
"eval_model_preparation_time": 0.0003,
|
| 1665 |
+
"eval_runtime": 24.5521,
|
| 1666 |
+
"eval_samples_per_second": 106.019,
|
| 1667 |
+
"eval_steps_per_second": 13.278,
|
| 1668 |
+
"step": 210
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.5468091998704243,
|
| 1672 |
+
"grad_norm": 2.140625,
|
| 1673 |
+
"learning_rate": 1.060918533505367e-05,
|
| 1674 |
+
"loss": 0.538,
|
| 1675 |
+
"step": 211
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.5494007126660188,
|
| 1679 |
+
"grad_norm": 3.1875,
|
| 1680 |
+
"learning_rate": 1.0515555206368815e-05,
|
| 1681 |
+
"loss": 0.53,
|
| 1682 |
+
"step": 212
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.5519922254616132,
|
| 1686 |
+
"grad_norm": 2.234375,
|
| 1687 |
+
"learning_rate": 1.0421879737620312e-05,
|
| 1688 |
+
"loss": 0.5315,
|
| 1689 |
+
"step": 213
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.5545837382572076,
|
| 1693 |
+
"grad_norm": 2.125,
|
| 1694 |
+
"learning_rate": 1.03281671670175e-05,
|
| 1695 |
+
"loss": 0.5408,
|
| 1696 |
+
"step": 214
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.5571752510528021,
|
| 1700 |
+
"grad_norm": 2.4375,
|
| 1701 |
+
"learning_rate": 1.0234425736032607e-05,
|
| 1702 |
+
"loss": 0.5436,
|
| 1703 |
+
"step": 215
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.5597667638483965,
|
| 1707 |
+
"grad_norm": 2.40625,
|
| 1708 |
+
"learning_rate": 1.014066368867596e-05,
|
| 1709 |
+
"loss": 0.5269,
|
| 1710 |
+
"step": 216
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.562358276643991,
|
| 1714 |
+
"grad_norm": 2.125,
|
| 1715 |
+
"learning_rate": 1.0046889270770987e-05,
|
| 1716 |
+
"loss": 0.5412,
|
| 1717 |
+
"step": 217
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.5649497894395854,
|
| 1721 |
+
"grad_norm": 2.3125,
|
| 1722 |
+
"learning_rate": 9.953110729229018e-06,
|
| 1723 |
+
"loss": 0.5346,
|
| 1724 |
+
"step": 218
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.5675413022351797,
|
| 1728 |
+
"grad_norm": 2.109375,
|
| 1729 |
+
"learning_rate": 9.859336311324042e-06,
|
| 1730 |
+
"loss": 0.5435,
|
| 1731 |
+
"step": 219
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.5701328150307742,
|
| 1735 |
+
"grad_norm": 2.125,
|
| 1736 |
+
"learning_rate": 9.765574263967397e-06,
|
| 1737 |
+
"loss": 0.5482,
|
| 1738 |
+
"step": 220
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.5701328150307742,
|
| 1742 |
+
"eval_loss": 0.5415154695510864,
|
| 1743 |
+
"eval_model_preparation_time": 0.0003,
|
| 1744 |
+
"eval_runtime": 24.571,
|
| 1745 |
+
"eval_samples_per_second": 105.938,
|
| 1746 |
+
"eval_steps_per_second": 13.268,
|
| 1747 |
+
"step": 220
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.5727243278263686,
|
| 1751 |
+
"grad_norm": 2.21875,
|
| 1752 |
+
"learning_rate": 9.671832832982502e-06,
|
| 1753 |
+
"loss": 0.5401,
|
| 1754 |
+
"step": 221
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.5753158406219631,
|
| 1758 |
+
"grad_norm": 2.3125,
|
| 1759 |
+
"learning_rate": 9.57812026237969e-06,
|
| 1760 |
+
"loss": 0.5359,
|
| 1761 |
+
"step": 222
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.5779073534175575,
|
| 1765 |
+
"grad_norm": 2.375,
|
| 1766 |
+
"learning_rate": 9.484444793631186e-06,
|
| 1767 |
+
"loss": 0.5366,
|
| 1768 |
+
"step": 223
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.5804988662131519,
|
| 1772 |
+
"grad_norm": 2.09375,
|
| 1773 |
+
"learning_rate": 9.390814664946332e-06,
|
| 1774 |
+
"loss": 0.5343,
|
| 1775 |
+
"step": 224
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.5830903790087464,
|
| 1779 |
+
"grad_norm": 2.03125,
|
| 1780 |
+
"learning_rate": 9.297238110547075e-06,
|
| 1781 |
+
"loss": 0.5385,
|
| 1782 |
+
"step": 225
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.5856818918043408,
|
| 1786 |
+
"grad_norm": 2.21875,
|
| 1787 |
+
"learning_rate": 9.203723359943802e-06,
|
| 1788 |
+
"loss": 0.5473,
|
| 1789 |
+
"step": 226
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.5882734045999352,
|
| 1793 |
+
"grad_norm": 2.53125,
|
| 1794 |
+
"learning_rate": 9.110278637211642e-06,
|
| 1795 |
+
"loss": 0.5316,
|
| 1796 |
+
"step": 227
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.5908649173955296,
|
| 1800 |
+
"grad_norm": 2.046875,
|
| 1801 |
+
"learning_rate": 9.016912160267168e-06,
|
| 1802 |
+
"loss": 0.53,
|
| 1803 |
+
"step": 228
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.593456430191124,
|
| 1807 |
+
"grad_norm": 2.4375,
|
| 1808 |
+
"learning_rate": 8.923632140145702e-06,
|
| 1809 |
+
"loss": 0.5497,
|
| 1810 |
+
"step": 229
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.5960479429867185,
|
| 1814 |
+
"grad_norm": 2.15625,
|
| 1815 |
+
"learning_rate": 8.830446780279175e-06,
|
| 1816 |
+
"loss": 0.5499,
|
| 1817 |
+
"step": 230
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.5960479429867185,
|
| 1821 |
+
"eval_loss": 0.5400256514549255,
|
| 1822 |
+
"eval_model_preparation_time": 0.0003,
|
| 1823 |
+
"eval_runtime": 24.5551,
|
| 1824 |
+
"eval_samples_per_second": 106.007,
|
| 1825 |
+
"eval_steps_per_second": 13.276,
|
| 1826 |
+
"step": 230
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.5986394557823129,
|
| 1830 |
+
"grad_norm": 2.15625,
|
| 1831 |
+
"learning_rate": 8.73736427577473e-06,
|
| 1832 |
+
"loss": 0.5301,
|
| 1833 |
+
"step": 231
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.6012309685779074,
|
| 1837 |
+
"grad_norm": 2.171875,
|
| 1838 |
+
"learning_rate": 8.644392812693969e-06,
|
| 1839 |
+
"loss": 0.5542,
|
| 1840 |
+
"step": 232
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 0.6038224813735018,
|
| 1844 |
+
"grad_norm": 2.1875,
|
| 1845 |
+
"learning_rate": 8.551540567333041e-06,
|
| 1846 |
+
"loss": 0.5374,
|
| 1847 |
+
"step": 233
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.6064139941690962,
|
| 1851 |
+
"grad_norm": 2.421875,
|
| 1852 |
+
"learning_rate": 8.458815705503612e-06,
|
| 1853 |
+
"loss": 0.549,
|
| 1854 |
+
"step": 234
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.6090055069646907,
|
| 1858 |
+
"grad_norm": 2.0625,
|
| 1859 |
+
"learning_rate": 8.366226381814698e-06,
|
| 1860 |
+
"loss": 0.5383,
|
| 1861 |
+
"step": 235
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.611597019760285,
|
| 1865 |
+
"grad_norm": 2.203125,
|
| 1866 |
+
"learning_rate": 8.273780738955545e-06,
|
| 1867 |
+
"loss": 0.5297,
|
| 1868 |
+
"step": 236
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.6141885325558795,
|
| 1872 |
+
"grad_norm": 2.140625,
|
| 1873 |
+
"learning_rate": 8.181486906979488e-06,
|
| 1874 |
+
"loss": 0.5303,
|
| 1875 |
+
"step": 237
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.6167800453514739,
|
| 1879 |
+
"grad_norm": 2.109375,
|
| 1880 |
+
"learning_rate": 8.089353002589003e-06,
|
| 1881 |
+
"loss": 0.5429,
|
| 1882 |
+
"step": 238
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.6193715581470683,
|
| 1886 |
+
"grad_norm": 2.171875,
|
| 1887 |
+
"learning_rate": 7.997387128421859e-06,
|
| 1888 |
+
"loss": 0.5442,
|
| 1889 |
+
"step": 239
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.6219630709426628,
|
| 1893 |
+
"grad_norm": 2.328125,
|
| 1894 |
+
"learning_rate": 7.905597372338558e-06,
|
| 1895 |
+
"loss": 0.5451,
|
| 1896 |
+
"step": 240
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.6219630709426628,
|
| 1900 |
+
"eval_loss": 0.5389755964279175,
|
| 1901 |
+
"eval_model_preparation_time": 0.0003,
|
| 1902 |
+
"eval_runtime": 24.5608,
|
| 1903 |
+
"eval_samples_per_second": 105.982,
|
| 1904 |
+
"eval_steps_per_second": 13.273,
|
| 1905 |
+
"step": 240
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.6245545837382572,
|
| 1909 |
+
"grad_norm": 2.078125,
|
| 1910 |
+
"learning_rate": 7.81399180671104e-06,
|
| 1911 |
+
"loss": 0.5392,
|
| 1912 |
+
"step": 241
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.6271460965338517,
|
| 1916 |
+
"grad_norm": 2.140625,
|
| 1917 |
+
"learning_rate": 7.722578487712776e-06,
|
| 1918 |
+
"loss": 0.5303,
|
| 1919 |
+
"step": 242
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.6297376093294461,
|
| 1923 |
+
"grad_norm": 2.15625,
|
| 1924 |
+
"learning_rate": 7.631365454610273e-06,
|
| 1925 |
+
"loss": 0.5387,
|
| 1926 |
+
"step": 243
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.6323291221250404,
|
| 1930 |
+
"grad_norm": 2.265625,
|
| 1931 |
+
"learning_rate": 7.540360729056059e-06,
|
| 1932 |
+
"loss": 0.5528,
|
| 1933 |
+
"step": 244
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.6349206349206349,
|
| 1937 |
+
"grad_norm": 2.15625,
|
| 1938 |
+
"learning_rate": 7.449572314383237e-06,
|
| 1939 |
+
"loss": 0.5488,
|
| 1940 |
+
"step": 245
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.6375121477162293,
|
| 1944 |
+
"grad_norm": 2.03125,
|
| 1945 |
+
"learning_rate": 7.359008194901633e-06,
|
| 1946 |
+
"loss": 0.5216,
|
| 1947 |
+
"step": 246
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.6401036605118238,
|
| 1951 |
+
"grad_norm": 2.15625,
|
| 1952 |
+
"learning_rate": 7.268676335195624e-06,
|
| 1953 |
+
"loss": 0.5314,
|
| 1954 |
+
"step": 247
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.6426951733074182,
|
| 1958 |
+
"grad_norm": 2.125,
|
| 1959 |
+
"learning_rate": 7.1785846794236945e-06,
|
| 1960 |
+
"loss": 0.5411,
|
| 1961 |
+
"step": 248
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.6452866861030127,
|
| 1965 |
+
"grad_norm": 2.140625,
|
| 1966 |
+
"learning_rate": 7.088741150619804e-06,
|
| 1967 |
+
"loss": 0.5272,
|
| 1968 |
+
"step": 249
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.6478781988986071,
|
| 1972 |
+
"grad_norm": 2.125,
|
| 1973 |
+
"learning_rate": 6.999153649996595e-06,
|
| 1974 |
+
"loss": 0.5344,
|
| 1975 |
+
"step": 250
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.6478781988986071,
|
| 1979 |
+
"eval_loss": 0.538066029548645,
|
| 1980 |
+
"eval_model_preparation_time": 0.0003,
|
| 1981 |
+
"eval_runtime": 24.5108,
|
| 1982 |
+
"eval_samples_per_second": 106.198,
|
| 1983 |
+
"eval_steps_per_second": 13.3,
|
| 1984 |
+
"step": 250
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.6504697116942015,
|
| 1988 |
+
"grad_norm": 2.09375,
|
| 1989 |
+
"learning_rate": 6.909830056250527e-06,
|
| 1990 |
+
"loss": 0.532,
|
| 1991 |
+
"step": 251
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.6530612244897959,
|
| 1995 |
+
"grad_norm": 2.09375,
|
| 1996 |
+
"learning_rate": 6.820778224868998e-06,
|
| 1997 |
+
"loss": 0.5376,
|
| 1998 |
+
"step": 252
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.6556527372853903,
|
| 2002 |
+
"grad_norm": 2.15625,
|
| 2003 |
+
"learning_rate": 6.732005987439494e-06,
|
| 2004 |
+
"loss": 0.5501,
|
| 2005 |
+
"step": 253
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.6582442500809847,
|
| 2009 |
+
"grad_norm": 2.0625,
|
| 2010 |
+
"learning_rate": 6.6435211509608546e-06,
|
| 2011 |
+
"loss": 0.532,
|
| 2012 |
+
"step": 254
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.6608357628765792,
|
| 2016 |
+
"grad_norm": 2.3125,
|
| 2017 |
+
"learning_rate": 6.555331497156671e-06,
|
| 2018 |
+
"loss": 0.5406,
|
| 2019 |
+
"step": 255
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.6634272756721736,
|
| 2023 |
+
"grad_norm": 2.03125,
|
| 2024 |
+
"learning_rate": 6.467444781790967e-06,
|
| 2025 |
+
"loss": 0.5249,
|
| 2026 |
+
"step": 256
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.6660187884677681,
|
| 2030 |
+
"grad_norm": 2.171875,
|
| 2031 |
+
"learning_rate": 6.379868733986089e-06,
|
| 2032 |
+
"loss": 0.5195,
|
| 2033 |
+
"step": 257
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.6686103012633625,
|
| 2037 |
+
"grad_norm": 2.1875,
|
| 2038 |
+
"learning_rate": 6.292611055542998e-06,
|
| 2039 |
+
"loss": 0.5397,
|
| 2040 |
+
"step": 258
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.671201814058957,
|
| 2044 |
+
"grad_norm": 2.21875,
|
| 2045 |
+
"learning_rate": 6.205679420263917e-06,
|
| 2046 |
+
"loss": 0.5455,
|
| 2047 |
+
"step": 259
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.6737933268545514,
|
| 2051 |
+
"grad_norm": 2.09375,
|
| 2052 |
+
"learning_rate": 6.119081473277502e-06,
|
| 2053 |
+
"loss": 0.5414,
|
| 2054 |
+
"step": 260
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.6737933268545514,
|
| 2058 |
+
"eval_loss": 0.5372032523155212,
|
| 2059 |
+
"eval_model_preparation_time": 0.0003,
|
| 2060 |
+
"eval_runtime": 24.5567,
|
| 2061 |
+
"eval_samples_per_second": 106.0,
|
| 2062 |
+
"eval_steps_per_second": 13.275,
|
| 2063 |
+
"step": 260
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 0.6763848396501457,
|
| 2067 |
+
"grad_norm": 2.5,
|
| 2068 |
+
"learning_rate": 6.032824830366466e-06,
|
| 2069 |
+
"loss": 0.5398,
|
| 2070 |
+
"step": 261
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 0.6789763524457402,
|
| 2074 |
+
"grad_norm": 2.109375,
|
| 2075 |
+
"learning_rate": 5.946917077297819e-06,
|
| 2076 |
+
"loss": 0.5512,
|
| 2077 |
+
"step": 262
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 0.6815678652413346,
|
| 2081 |
+
"grad_norm": 2.125,
|
| 2082 |
+
"learning_rate": 5.86136576915576e-06,
|
| 2083 |
+
"loss": 0.5486,
|
| 2084 |
+
"step": 263
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.6841593780369291,
|
| 2088 |
+
"grad_norm": 2.203125,
|
| 2089 |
+
"learning_rate": 5.7761784296772395e-06,
|
| 2090 |
+
"loss": 0.543,
|
| 2091 |
+
"step": 264
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.6867508908325235,
|
| 2095 |
+
"grad_norm": 2.171875,
|
| 2096 |
+
"learning_rate": 5.6913625505902966e-06,
|
| 2097 |
+
"loss": 0.5065,
|
| 2098 |
+
"step": 265
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 0.6893424036281179,
|
| 2102 |
+
"grad_norm": 2.171875,
|
| 2103 |
+
"learning_rate": 5.6069255909551986e-06,
|
| 2104 |
+
"loss": 0.5328,
|
| 2105 |
+
"step": 266
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 0.6919339164237124,
|
| 2109 |
+
"grad_norm": 2.015625,
|
| 2110 |
+
"learning_rate": 5.522874976508464e-06,
|
| 2111 |
+
"loss": 0.5404,
|
| 2112 |
+
"step": 267
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 0.6945254292193068,
|
| 2116 |
+
"grad_norm": 1.9375,
|
| 2117 |
+
"learning_rate": 5.439218099009822e-06,
|
| 2118 |
+
"loss": 0.528,
|
| 2119 |
+
"step": 268
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 0.6971169420149012,
|
| 2123 |
+
"grad_norm": 2.0625,
|
| 2124 |
+
"learning_rate": 5.355962315592118e-06,
|
| 2125 |
+
"loss": 0.5377,
|
| 2126 |
+
"step": 269
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.6997084548104956,
|
| 2130 |
+
"grad_norm": 2.078125,
|
| 2131 |
+
"learning_rate": 5.273114948114346e-06,
|
| 2132 |
+
"loss": 0.5361,
|
| 2133 |
+
"step": 270
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.6997084548104956,
|
| 2137 |
+
"eval_loss": 0.5366343259811401,
|
| 2138 |
+
"eval_model_preparation_time": 0.0003,
|
| 2139 |
+
"eval_runtime": 24.5782,
|
| 2140 |
+
"eval_samples_per_second": 105.907,
|
| 2141 |
+
"eval_steps_per_second": 13.264,
|
| 2142 |
+
"step": 270
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.70229996760609,
|
| 2146 |
+
"grad_norm": 2.203125,
|
| 2147 |
+
"learning_rate": 5.190683282517701e-06,
|
| 2148 |
+
"loss": 0.5295,
|
| 2149 |
+
"step": 271
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 0.7048914804016845,
|
| 2153 |
+
"grad_norm": 2.15625,
|
| 2154 |
+
"learning_rate": 5.108674568184822e-06,
|
| 2155 |
+
"loss": 0.5333,
|
| 2156 |
+
"step": 272
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.7074829931972789,
|
| 2160 |
+
"grad_norm": 2.0,
|
| 2161 |
+
"learning_rate": 5.027096017302261e-06,
|
| 2162 |
+
"loss": 0.525,
|
| 2163 |
+
"step": 273
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.7100745059928734,
|
| 2167 |
+
"grad_norm": 2.140625,
|
| 2168 |
+
"learning_rate": 4.945954804226214e-06,
|
| 2169 |
+
"loss": 0.5328,
|
| 2170 |
+
"step": 274
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.7126660187884678,
|
| 2174 |
+
"grad_norm": 1.953125,
|
| 2175 |
+
"learning_rate": 4.865258064851579e-06,
|
| 2176 |
+
"loss": 0.5453,
|
| 2177 |
+
"step": 275
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 0.7152575315840622,
|
| 2181 |
+
"grad_norm": 2.109375,
|
| 2182 |
+
"learning_rate": 4.785012895984397e-06,
|
| 2183 |
+
"loss": 0.537,
|
| 2184 |
+
"step": 276
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 0.7178490443796566,
|
| 2188 |
+
"grad_norm": 1.9609375,
|
| 2189 |
+
"learning_rate": 4.705226354717704e-06,
|
| 2190 |
+
"loss": 0.5459,
|
| 2191 |
+
"step": 277
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 0.720440557175251,
|
| 2195 |
+
"grad_norm": 1.9296875,
|
| 2196 |
+
"learning_rate": 4.625905457810943e-06,
|
| 2197 |
+
"loss": 0.5444,
|
| 2198 |
+
"step": 278
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.7230320699708455,
|
| 2202 |
+
"grad_norm": 2.25,
|
| 2203 |
+
"learning_rate": 4.547057181072861e-06,
|
| 2204 |
+
"loss": 0.532,
|
| 2205 |
+
"step": 279
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.7256235827664399,
|
| 2209 |
+
"grad_norm": 2.046875,
|
| 2210 |
+
"learning_rate": 4.468688458748006e-06,
|
| 2211 |
+
"loss": 0.5209,
|
| 2212 |
+
"step": 280
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 0.7256235827664399,
|
| 2216 |
+
"eval_loss": 0.5361185073852539,
|
| 2217 |
+
"eval_model_preparation_time": 0.0003,
|
| 2218 |
+
"eval_runtime": 24.5554,
|
| 2219 |
+
"eval_samples_per_second": 106.005,
|
| 2220 |
+
"eval_steps_per_second": 13.276,
|
| 2221 |
+
"step": 280
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.7282150955620343,
|
| 2225 |
+
"grad_norm": 1.9375,
|
| 2226 |
+
"learning_rate": 4.390806182906946e-06,
|
| 2227 |
+
"loss": 0.5304,
|
| 2228 |
+
"step": 281
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.7308066083576288,
|
| 2232 |
+
"grad_norm": 1.9921875,
|
| 2233 |
+
"learning_rate": 4.313417202840106e-06,
|
| 2234 |
+
"loss": 0.5532,
|
| 2235 |
+
"step": 282
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.7333981211532232,
|
| 2239 |
+
"grad_norm": 2.265625,
|
| 2240 |
+
"learning_rate": 4.2365283244554545e-06,
|
| 2241 |
+
"loss": 0.5358,
|
| 2242 |
+
"step": 283
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.7359896339488177,
|
| 2246 |
+
"grad_norm": 2.34375,
|
| 2247 |
+
"learning_rate": 4.160146309679928e-06,
|
| 2248 |
+
"loss": 0.5444,
|
| 2249 |
+
"step": 284
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.738581146744412,
|
| 2253 |
+
"grad_norm": 2.171875,
|
| 2254 |
+
"learning_rate": 4.084277875864776e-06,
|
| 2255 |
+
"loss": 0.5374,
|
| 2256 |
+
"step": 285
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.7411726595400064,
|
| 2260 |
+
"grad_norm": 2.53125,
|
| 2261 |
+
"learning_rate": 4.008929695194819e-06,
|
| 2262 |
+
"loss": 0.5441,
|
| 2263 |
+
"step": 286
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.7437641723356009,
|
| 2267 |
+
"grad_norm": 2.71875,
|
| 2268 |
+
"learning_rate": 3.934108394101645e-06,
|
| 2269 |
+
"loss": 0.5383,
|
| 2270 |
+
"step": 287
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.7463556851311953,
|
| 2274 |
+
"grad_norm": 2.3125,
|
| 2275 |
+
"learning_rate": 3.859820552680867e-06,
|
| 2276 |
+
"loss": 0.5481,
|
| 2277 |
+
"step": 288
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.7489471979267898,
|
| 2281 |
+
"grad_norm": 2.359375,
|
| 2282 |
+
"learning_rate": 3.786072704113456e-06,
|
| 2283 |
+
"loss": 0.5435,
|
| 2284 |
+
"step": 289
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.7515387107223842,
|
| 2288 |
+
"grad_norm": 2.0,
|
| 2289 |
+
"learning_rate": 3.712871334091154e-06,
|
| 2290 |
+
"loss": 0.5247,
|
| 2291 |
+
"step": 290
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.7515387107223842,
|
| 2295 |
+
"eval_loss": 0.5358829498291016,
|
| 2296 |
+
"eval_model_preparation_time": 0.0003,
|
| 2297 |
+
"eval_runtime": 24.5374,
|
| 2298 |
+
"eval_samples_per_second": 106.083,
|
| 2299 |
+
"eval_steps_per_second": 13.286,
|
| 2300 |
+
"step": 290
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.7541302235179786,
|
| 2304 |
+
"grad_norm": 2.03125,
|
| 2305 |
+
"learning_rate": 3.640222880246117e-06,
|
| 2306 |
+
"loss": 0.5215,
|
| 2307 |
+
"step": 291
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.7567217363135731,
|
| 2311 |
+
"grad_norm": 2.09375,
|
| 2312 |
+
"learning_rate": 3.5681337315847677e-06,
|
| 2313 |
+
"loss": 0.5337,
|
| 2314 |
+
"step": 292
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.7593132491091675,
|
| 2318 |
+
"grad_norm": 1.9609375,
|
| 2319 |
+
"learning_rate": 3.4966102279258964e-06,
|
| 2320 |
+
"loss": 0.5353,
|
| 2321 |
+
"step": 293
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.7619047619047619,
|
| 2325 |
+
"grad_norm": 1.984375,
|
| 2326 |
+
"learning_rate": 3.425658659343141e-06,
|
| 2327 |
+
"loss": 0.5454,
|
| 2328 |
+
"step": 294
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 0.7644962747003563,
|
| 2332 |
+
"grad_norm": 2.046875,
|
| 2333 |
+
"learning_rate": 3.355285265611784e-06,
|
| 2334 |
+
"loss": 0.5172,
|
| 2335 |
+
"step": 295
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 0.7670877874959507,
|
| 2339 |
+
"grad_norm": 1.9765625,
|
| 2340 |
+
"learning_rate": 3.285496235660013e-06,
|
| 2341 |
+
"loss": 0.5267,
|
| 2342 |
+
"step": 296
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.7696793002915452,
|
| 2346 |
+
"grad_norm": 1.9765625,
|
| 2347 |
+
"learning_rate": 3.216297707024655e-06,
|
| 2348 |
+
"loss": 0.5436,
|
| 2349 |
+
"step": 297
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.7722708130871396,
|
| 2353 |
+
"grad_norm": 2.1875,
|
| 2354 |
+
"learning_rate": 3.147695765311377e-06,
|
| 2355 |
+
"loss": 0.5349,
|
| 2356 |
+
"step": 298
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.7748623258827341,
|
| 2360 |
+
"grad_norm": 2.0,
|
| 2361 |
+
"learning_rate": 3.079696443659538e-06,
|
| 2362 |
+
"loss": 0.5437,
|
| 2363 |
+
"step": 299
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 0.7774538386783285,
|
| 2367 |
+
"grad_norm": 2.046875,
|
| 2368 |
+
"learning_rate": 3.0123057222115835e-06,
|
| 2369 |
+
"loss": 0.5185,
|
| 2370 |
+
"step": 300
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 0.7774538386783285,
|
| 2374 |
+
"eval_loss": 0.5356724858283997,
|
| 2375 |
+
"eval_model_preparation_time": 0.0003,
|
| 2376 |
+
"eval_runtime": 24.5736,
|
| 2377 |
+
"eval_samples_per_second": 105.927,
|
| 2378 |
+
"eval_steps_per_second": 13.266,
|
| 2379 |
+
"step": 300
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 0.780045351473923,
|
| 2383 |
+
"grad_norm": 2.109375,
|
| 2384 |
+
"learning_rate": 2.94552952758713e-06,
|
| 2385 |
+
"loss": 0.5204,
|
| 2386 |
+
"step": 301
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 0.7826368642695173,
|
| 2390 |
+
"grad_norm": 1.953125,
|
| 2391 |
+
"learning_rate": 2.8793737323617554e-06,
|
| 2392 |
+
"loss": 0.5483,
|
| 2393 |
+
"step": 302
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 0.7852283770651117,
|
| 2397 |
+
"grad_norm": 1.9140625,
|
| 2398 |
+
"learning_rate": 2.813844154550537e-06,
|
| 2399 |
+
"loss": 0.5433,
|
| 2400 |
+
"step": 303
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 0.7878198898607062,
|
| 2404 |
+
"grad_norm": 1.953125,
|
| 2405 |
+
"learning_rate": 2.748946557096407e-06,
|
| 2406 |
+
"loss": 0.5374,
|
| 2407 |
+
"step": 304
|
| 2408 |
+
},
|
| 2409 |
+
{
|
| 2410 |
+
"epoch": 0.7904114026563006,
|
| 2411 |
+
"grad_norm": 2.125,
|
| 2412 |
+
"learning_rate": 2.6846866473633126e-06,
|
| 2413 |
+
"loss": 0.5405,
|
| 2414 |
+
"step": 305
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 0.793002915451895,
|
| 2418 |
+
"grad_norm": 2.0,
|
| 2419 |
+
"learning_rate": 2.621070076634297e-06,
|
| 2420 |
+
"loss": 0.535,
|
| 2421 |
+
"step": 306
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 0.7955944282474895,
|
| 2425 |
+
"grad_norm": 2.09375,
|
| 2426 |
+
"learning_rate": 2.5581024396145116e-06,
|
| 2427 |
+
"loss": 0.5474,
|
| 2428 |
+
"step": 307
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 0.7981859410430839,
|
| 2432 |
+
"grad_norm": 1.9296875,
|
| 2433 |
+
"learning_rate": 2.4957892739391764e-06,
|
| 2434 |
+
"loss": 0.5288,
|
| 2435 |
+
"step": 308
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 0.8007774538386784,
|
| 2439 |
+
"grad_norm": 2.453125,
|
| 2440 |
+
"learning_rate": 2.434136059686587e-06,
|
| 2441 |
+
"loss": 0.5437,
|
| 2442 |
+
"step": 309
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 0.8033689666342727,
|
| 2446 |
+
"grad_norm": 2.171875,
|
| 2447 |
+
"learning_rate": 2.373148218896182e-06,
|
| 2448 |
+
"loss": 0.5377,
|
| 2449 |
+
"step": 310
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 0.8033689666342727,
|
| 2453 |
+
"eval_loss": 0.5354843139648438,
|
| 2454 |
+
"eval_model_preparation_time": 0.0003,
|
| 2455 |
+
"eval_runtime": 24.623,
|
| 2456 |
+
"eval_samples_per_second": 105.714,
|
| 2457 |
+
"eval_steps_per_second": 13.24,
|
| 2458 |
+
"step": 310
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 0.8059604794298671,
|
| 2462 |
+
"grad_norm": 2.09375,
|
| 2463 |
+
"learning_rate": 2.312831115091683e-06,
|
| 2464 |
+
"loss": 0.545,
|
| 2465 |
+
"step": 311
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 0.8085519922254616,
|
| 2469 |
+
"grad_norm": 1.984375,
|
| 2470 |
+
"learning_rate": 2.2531900528094342e-06,
|
| 2471 |
+
"loss": 0.5291,
|
| 2472 |
+
"step": 312
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 0.811143505021056,
|
| 2476 |
+
"grad_norm": 2.09375,
|
| 2477 |
+
"learning_rate": 2.1942302771318713e-06,
|
| 2478 |
+
"loss": 0.5306,
|
| 2479 |
+
"step": 313
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 0.8137350178166505,
|
| 2483 |
+
"grad_norm": 2.125,
|
| 2484 |
+
"learning_rate": 2.135956973226262e-06,
|
| 2485 |
+
"loss": 0.5352,
|
| 2486 |
+
"step": 314
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.8163265306122449,
|
| 2490 |
+
"grad_norm": 2.28125,
|
| 2491 |
+
"learning_rate": 2.078375265888707e-06,
|
| 2492 |
+
"loss": 0.5209,
|
| 2493 |
+
"step": 315
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 0.8189180434078394,
|
| 2497 |
+
"grad_norm": 2.109375,
|
| 2498 |
+
"learning_rate": 2.021490219093426e-06,
|
| 2499 |
+
"loss": 0.5331,
|
| 2500 |
+
"step": 316
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 0.8215095562034338,
|
| 2504 |
+
"grad_norm": 2.15625,
|
| 2505 |
+
"learning_rate": 1.9653068355474213e-06,
|
| 2506 |
+
"loss": 0.5317,
|
| 2507 |
+
"step": 317
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 0.8241010689990281,
|
| 2511 |
+
"grad_norm": 2.171875,
|
| 2512 |
+
"learning_rate": 1.9098300562505266e-06,
|
| 2513 |
+
"loss": 0.5378,
|
| 2514 |
+
"step": 318
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 0.8266925817946226,
|
| 2518 |
+
"grad_norm": 2.09375,
|
| 2519 |
+
"learning_rate": 1.8550647600608573e-06,
|
| 2520 |
+
"loss": 0.5243,
|
| 2521 |
+
"step": 319
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.829284094590217,
|
| 2525 |
+
"grad_norm": 2.3125,
|
| 2526 |
+
"learning_rate": 1.8010157632657544e-06,
|
| 2527 |
+
"loss": 0.5229,
|
| 2528 |
+
"step": 320
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 0.829284094590217,
|
| 2532 |
+
"eval_loss": 0.5353964567184448,
|
| 2533 |
+
"eval_model_preparation_time": 0.0003,
|
| 2534 |
+
"eval_runtime": 24.5807,
|
| 2535 |
+
"eval_samples_per_second": 105.896,
|
| 2536 |
+
"eval_steps_per_second": 13.262,
|
| 2537 |
+
"step": 320
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.8318756073858115,
|
| 2541 |
+
"grad_norm": 2.21875,
|
| 2542 |
+
"learning_rate": 1.7476878191582247e-06,
|
| 2543 |
+
"loss": 0.5288,
|
| 2544 |
+
"step": 321
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.8344671201814059,
|
| 2548 |
+
"grad_norm": 1.90625,
|
| 2549 |
+
"learning_rate": 1.6950856176189034e-06,
|
| 2550 |
+
"loss": 0.5234,
|
| 2551 |
+
"step": 322
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.8370586329770003,
|
| 2555 |
+
"grad_norm": 2.09375,
|
| 2556 |
+
"learning_rate": 1.6432137847036144e-06,
|
| 2557 |
+
"loss": 0.5598,
|
| 2558 |
+
"step": 323
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.8396501457725948,
|
| 2562 |
+
"grad_norm": 2.03125,
|
| 2563 |
+
"learning_rate": 1.5920768822365418e-06,
|
| 2564 |
+
"loss": 0.5302,
|
| 2565 |
+
"step": 324
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.8422416585681892,
|
| 2569 |
+
"grad_norm": 2.078125,
|
| 2570 |
+
"learning_rate": 1.5416794074090258e-06,
|
| 2571 |
+
"loss": 0.5338,
|
| 2572 |
+
"step": 325
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.8448331713637837,
|
| 2576 |
+
"grad_norm": 2.1875,
|
| 2577 |
+
"learning_rate": 1.4920257923840865e-06,
|
| 2578 |
+
"loss": 0.5408,
|
| 2579 |
+
"step": 326
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.847424684159378,
|
| 2583 |
+
"grad_norm": 2.09375,
|
| 2584 |
+
"learning_rate": 1.4431204039066082e-06,
|
| 2585 |
+
"loss": 0.5297,
|
| 2586 |
+
"step": 327
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.8500161969549724,
|
| 2590 |
+
"grad_norm": 2.125,
|
| 2591 |
+
"learning_rate": 1.3949675429193465e-06,
|
| 2592 |
+
"loss": 0.518,
|
| 2593 |
+
"step": 328
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.8526077097505669,
|
| 2597 |
+
"grad_norm": 2.1875,
|
| 2598 |
+
"learning_rate": 1.347571444184661e-06,
|
| 2599 |
+
"loss": 0.5271,
|
| 2600 |
+
"step": 329
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.8551992225461613,
|
| 2604 |
+
"grad_norm": 2.5625,
|
| 2605 |
+
"learning_rate": 1.300936275912098e-06,
|
| 2606 |
+
"loss": 0.5267,
|
| 2607 |
+
"step": 330
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.8551992225461613,
|
| 2611 |
+
"eval_loss": 0.5353734493255615,
|
| 2612 |
+
"eval_model_preparation_time": 0.0003,
|
| 2613 |
+
"eval_runtime": 24.6222,
|
| 2614 |
+
"eval_samples_per_second": 105.718,
|
| 2615 |
+
"eval_steps_per_second": 13.24,
|
| 2616 |
+
"step": 330
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 0.8577907353417558,
|
| 2620 |
+
"grad_norm": 2.1875,
|
| 2621 |
+
"learning_rate": 1.2550661393918217e-06,
|
| 2622 |
+
"loss": 0.5435,
|
| 2623 |
+
"step": 331
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 0.8603822481373502,
|
| 2627 |
+
"grad_norm": 2.25,
|
| 2628 |
+
"learning_rate": 1.2099650686339304e-06,
|
| 2629 |
+
"loss": 0.5395,
|
| 2630 |
+
"step": 332
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 0.8629737609329446,
|
| 2634 |
+
"grad_norm": 1.984375,
|
| 2635 |
+
"learning_rate": 1.1656370300136944e-06,
|
| 2636 |
+
"loss": 0.5279,
|
| 2637 |
+
"step": 333
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 0.8655652737285391,
|
| 2641 |
+
"grad_norm": 2.078125,
|
| 2642 |
+
"learning_rate": 1.122085921922723e-06,
|
| 2643 |
+
"loss": 0.5208,
|
| 2644 |
+
"step": 334
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"epoch": 0.8681567865241334,
|
| 2648 |
+
"grad_norm": 2.0625,
|
| 2649 |
+
"learning_rate": 1.0793155744261352e-06,
|
| 2650 |
+
"loss": 0.5387,
|
| 2651 |
+
"step": 335
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 0.8707482993197279,
|
| 2655 |
+
"grad_norm": 2.09375,
|
| 2656 |
+
"learning_rate": 1.0373297489257273e-06,
|
| 2657 |
+
"loss": 0.557,
|
| 2658 |
+
"step": 336
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 0.8733398121153223,
|
| 2662 |
+
"grad_norm": 2.015625,
|
| 2663 |
+
"learning_rate": 9.96132137829171e-07,
|
| 2664 |
+
"loss": 0.5282,
|
| 2665 |
+
"step": 337
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 0.8759313249109167,
|
| 2669 |
+
"grad_norm": 2.109375,
|
| 2670 |
+
"learning_rate": 9.557263642252946e-07,
|
| 2671 |
+
"loss": 0.5393,
|
| 2672 |
+
"step": 338
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 0.8785228377065112,
|
| 2676 |
+
"grad_norm": 2.46875,
|
| 2677 |
+
"learning_rate": 9.161159815654574e-07,
|
| 2678 |
+
"loss": 0.5283,
|
| 2679 |
+
"step": 339
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 0.8811143505021056,
|
| 2683 |
+
"grad_norm": 2.265625,
|
| 2684 |
+
"learning_rate": 8.773044733510338e-07,
|
| 2685 |
+
"loss": 0.5238,
|
| 2686 |
+
"step": 340
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 0.8811143505021056,
|
| 2690 |
+
"eval_loss": 0.535314679145813,
|
| 2691 |
+
"eval_model_preparation_time": 0.0003,
|
| 2692 |
+
"eval_runtime": 24.5977,
|
| 2693 |
+
"eval_samples_per_second": 105.823,
|
| 2694 |
+
"eval_steps_per_second": 13.253,
|
| 2695 |
+
"step": 340
|
| 2696 |
+
},
|
| 2697 |
+
{
|
| 2698 |
+
"epoch": 0.8837058632977001,
|
| 2699 |
+
"grad_norm": 1.9609375,
|
| 2700 |
+
"learning_rate": 8.392952528270659e-07,
|
| 2701 |
+
"loss": 0.5426,
|
| 2702 |
+
"step": 341
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 0.8862973760932945,
|
| 2706 |
+
"grad_norm": 3.515625,
|
| 2707 |
+
"learning_rate": 8.020916626820919e-07,
|
| 2708 |
+
"loss": 0.5267,
|
| 2709 |
+
"step": 342
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 0.8888888888888888,
|
| 2713 |
+
"grad_norm": 2.1875,
|
| 2714 |
+
"learning_rate": 7.656969747541664e-07,
|
| 2715 |
+
"loss": 0.5243,
|
| 2716 |
+
"step": 343
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 0.8914804016844833,
|
| 2720 |
+
"grad_norm": 2.0,
|
| 2721 |
+
"learning_rate": 7.30114389743134e-07,
|
| 2722 |
+
"loss": 0.5388,
|
| 2723 |
+
"step": 344
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 0.8940719144800777,
|
| 2727 |
+
"grad_norm": 1.9453125,
|
| 2728 |
+
"learning_rate": 6.953470369291349e-07,
|
| 2729 |
+
"loss": 0.547,
|
| 2730 |
+
"step": 345
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 0.8966634272756722,
|
| 2734 |
+
"grad_norm": 2.015625,
|
| 2735 |
+
"learning_rate": 6.613979738974075e-07,
|
| 2736 |
+
"loss": 0.5232,
|
| 2737 |
+
"step": 346
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"epoch": 0.8992549400712666,
|
| 2741 |
+
"grad_norm": 2.109375,
|
| 2742 |
+
"learning_rate": 6.282701862693963e-07,
|
| 2743 |
+
"loss": 0.526,
|
| 2744 |
+
"step": 347
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 0.901846452866861,
|
| 2748 |
+
"grad_norm": 2.09375,
|
| 2749 |
+
"learning_rate": 5.959665874401766e-07,
|
| 2750 |
+
"loss": 0.5216,
|
| 2751 |
+
"step": 348
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 0.9044379656624555,
|
| 2755 |
+
"grad_norm": 2.875,
|
| 2756 |
+
"learning_rate": 5.64490018322239e-07,
|
| 2757 |
+
"loss": 0.5212,
|
| 2758 |
+
"step": 349
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"epoch": 0.9070294784580499,
|
| 2762 |
+
"grad_norm": 2.140625,
|
| 2763 |
+
"learning_rate": 5.33843247095659e-07,
|
| 2764 |
+
"loss": 0.5363,
|
| 2765 |
+
"step": 350
|
| 2766 |
+
},
|
| 2767 |
+
{
|
| 2768 |
+
"epoch": 0.9070294784580499,
|
| 2769 |
+
"eval_loss": 0.5353750586509705,
|
| 2770 |
+
"eval_model_preparation_time": 0.0003,
|
| 2771 |
+
"eval_runtime": 24.5397,
|
| 2772 |
+
"eval_samples_per_second": 106.073,
|
| 2773 |
+
"eval_steps_per_second": 13.285,
|
| 2774 |
+
"step": 350
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.9096209912536443,
|
| 2778 |
+
"grad_norm": 2.1875,
|
| 2779 |
+
"learning_rate": 5.040289689646338e-07,
|
| 2780 |
+
"loss": 0.5363,
|
| 2781 |
+
"step": 351
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.9122125040492387,
|
| 2785 |
+
"grad_norm": 2.03125,
|
| 2786 |
+
"learning_rate": 4.750498059204678e-07,
|
| 2787 |
+
"loss": 0.5409,
|
| 2788 |
+
"step": 352
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.9148040168448331,
|
| 2792 |
+
"grad_norm": 2.015625,
|
| 2793 |
+
"learning_rate": 4.469083065109825e-07,
|
| 2794 |
+
"loss": 0.514,
|
| 2795 |
+
"step": 353
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.9173955296404276,
|
| 2799 |
+
"grad_norm": 2.21875,
|
| 2800 |
+
"learning_rate": 4.196069456163787e-07,
|
| 2801 |
+
"loss": 0.5272,
|
| 2802 |
+
"step": 354
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.919987042436022,
|
| 2806 |
+
"grad_norm": 1.859375,
|
| 2807 |
+
"learning_rate": 3.931481242315993e-07,
|
| 2808 |
+
"loss": 0.542,
|
| 2809 |
+
"step": 355
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.9225785552316165,
|
| 2813 |
+
"grad_norm": 1.96875,
|
| 2814 |
+
"learning_rate": 3.6753416925515596e-07,
|
| 2815 |
+
"loss": 0.5248,
|
| 2816 |
+
"step": 356
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.9251700680272109,
|
| 2820 |
+
"grad_norm": 2.046875,
|
| 2821 |
+
"learning_rate": 3.427673332845138e-07,
|
| 2822 |
+
"loss": 0.5215,
|
| 2823 |
+
"step": 357
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.9277615808228054,
|
| 2827 |
+
"grad_norm": 1.90625,
|
| 2828 |
+
"learning_rate": 3.188497944179758e-07,
|
| 2829 |
+
"loss": 0.5354,
|
| 2830 |
+
"step": 358
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 0.9303530936183998,
|
| 2834 |
+
"grad_norm": 2.03125,
|
| 2835 |
+
"learning_rate": 2.9578365606312666e-07,
|
| 2836 |
+
"loss": 0.53,
|
| 2837 |
+
"step": 359
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.9329446064139941,
|
| 2841 |
+
"grad_norm": 2.109375,
|
| 2842 |
+
"learning_rate": 2.735709467518699e-07,
|
| 2843 |
+
"loss": 0.5356,
|
| 2844 |
+
"step": 360
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.9329446064139941,
|
| 2848 |
+
"eval_loss": 0.5352712273597717,
|
| 2849 |
+
"eval_model_preparation_time": 0.0003,
|
| 2850 |
+
"eval_runtime": 24.5757,
|
| 2851 |
+
"eval_samples_per_second": 105.918,
|
| 2852 |
+
"eval_steps_per_second": 13.265,
|
| 2853 |
+
"step": 360
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 0.9355361192095886,
|
| 2857 |
+
"grad_norm": 2.140625,
|
| 2858 |
+
"learning_rate": 2.522136199620095e-07,
|
| 2859 |
+
"loss": 0.5191,
|
| 2860 |
+
"step": 361
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 0.938127632005183,
|
| 2864 |
+
"grad_norm": 2.21875,
|
| 2865 |
+
"learning_rate": 2.3171355394546625e-07,
|
| 2866 |
+
"loss": 0.539,
|
| 2867 |
+
"step": 362
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 0.9407191448007775,
|
| 2871 |
+
"grad_norm": 2.0,
|
| 2872 |
+
"learning_rate": 2.120725515630906e-07,
|
| 2873 |
+
"loss": 0.5342,
|
| 2874 |
+
"step": 363
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.9433106575963719,
|
| 2878 |
+
"grad_norm": 2.203125,
|
| 2879 |
+
"learning_rate": 1.932923401261133e-07,
|
| 2880 |
+
"loss": 0.5382,
|
| 2881 |
+
"step": 364
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.9459021703919663,
|
| 2885 |
+
"grad_norm": 1.9296875,
|
| 2886 |
+
"learning_rate": 1.7537457124423896e-07,
|
| 2887 |
+
"loss": 0.5371,
|
| 2888 |
+
"step": 365
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.9484936831875608,
|
| 2892 |
+
"grad_norm": 2.1875,
|
| 2893 |
+
"learning_rate": 1.5832082068039545e-07,
|
| 2894 |
+
"loss": 0.5303,
|
| 2895 |
+
"step": 366
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 0.9510851959831552,
|
| 2899 |
+
"grad_norm": 2.125,
|
| 2900 |
+
"learning_rate": 1.421325882121538e-07,
|
| 2901 |
+
"loss": 0.5178,
|
| 2902 |
+
"step": 367
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 0.9536767087787495,
|
| 2906 |
+
"grad_norm": 2.03125,
|
| 2907 |
+
"learning_rate": 1.2681129749983811e-07,
|
| 2908 |
+
"loss": 0.5309,
|
| 2909 |
+
"step": 368
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 0.956268221574344,
|
| 2913 |
+
"grad_norm": 2.09375,
|
| 2914 |
+
"learning_rate": 1.1235829596131231e-07,
|
| 2915 |
+
"loss": 0.536,
|
| 2916 |
+
"step": 369
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 0.9588597343699384,
|
| 2920 |
+
"grad_norm": 2.109375,
|
| 2921 |
+
"learning_rate": 9.877485465349057e-08,
|
| 2922 |
+
"loss": 0.5315,
|
| 2923 |
+
"step": 370
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 0.9588597343699384,
|
| 2927 |
+
"eval_loss": 0.5353068113327026,
|
| 2928 |
+
"eval_model_preparation_time": 0.0003,
|
| 2929 |
+
"eval_runtime": 24.5295,
|
| 2930 |
+
"eval_samples_per_second": 106.117,
|
| 2931 |
+
"eval_steps_per_second": 13.29,
|
| 2932 |
+
"step": 370
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 0.9614512471655329,
|
| 2936 |
+
"grad_norm": 1.9609375,
|
| 2937 |
+
"learning_rate": 8.606216816055336e-08,
|
| 2938 |
+
"loss": 0.5176,
|
| 2939 |
+
"step": 371
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 0.9640427599611273,
|
| 2943 |
+
"grad_norm": 2.03125,
|
| 2944 |
+
"learning_rate": 7.422135448889034e-08,
|
| 2945 |
+
"loss": 0.5252,
|
| 2946 |
+
"step": 372
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 0.9666342727567218,
|
| 2950 |
+
"grad_norm": 2.46875,
|
| 2951 |
+
"learning_rate": 6.325345496877688e-08,
|
| 2952 |
+
"loss": 0.5599,
|
| 2953 |
+
"step": 373
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 0.9692257855523162,
|
| 2957 |
+
"grad_norm": 2.140625,
|
| 2958 |
+
"learning_rate": 5.315943416279834e-08,
|
| 2959 |
+
"loss": 0.5342,
|
| 2960 |
+
"step": 374
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 0.9718172983479106,
|
| 2964 |
+
"grad_norm": 2.140625,
|
| 2965 |
+
"learning_rate": 4.394017978101905e-08,
|
| 2966 |
+
"loss": 0.5183,
|
| 2967 |
+
"step": 375
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 0.974408811143505,
|
| 2971 |
+
"grad_norm": 1.984375,
|
| 2972 |
+
"learning_rate": 3.5596502602917024e-08,
|
| 2973 |
+
"loss": 0.5256,
|
| 2974 |
+
"step": 376
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 0.9770003239390994,
|
| 2978 |
+
"grad_norm": 2.171875,
|
| 2979 |
+
"learning_rate": 2.8129136406075397e-08,
|
| 2980 |
+
"loss": 0.5406,
|
| 2981 |
+
"step": 377
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 0.9795918367346939,
|
| 2985 |
+
"grad_norm": 2.0,
|
| 2986 |
+
"learning_rate": 2.1538737901658503e-08,
|
| 2987 |
+
"loss": 0.5329,
|
| 2988 |
+
"step": 378
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 0.9821833495302883,
|
| 2992 |
+
"grad_norm": 1.9765625,
|
| 2993 |
+
"learning_rate": 1.5825886676649195e-08,
|
| 2994 |
+
"loss": 0.5575,
|
| 2995 |
+
"step": 379
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 0.9847748623258827,
|
| 2999 |
+
"grad_norm": 1.9375,
|
| 3000 |
+
"learning_rate": 1.099108514288627e-08,
|
| 3001 |
+
"loss": 0.5297,
|
| 3002 |
+
"step": 380
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.9847748623258827,
|
| 3006 |
+
"eval_loss": 0.535337507724762,
|
| 3007 |
+
"eval_model_preparation_time": 0.0003,
|
| 3008 |
+
"eval_runtime": 24.5539,
|
| 3009 |
+
"eval_samples_per_second": 106.012,
|
| 3010 |
+
"eval_steps_per_second": 13.277,
|
| 3011 |
+
"step": 380
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 0.9873663751214772,
|
| 3015 |
+
"grad_norm": 2.125,
|
| 3016 |
+
"learning_rate": 7.034758492872051e-09,
|
| 3017 |
+
"loss": 0.5427,
|
| 3018 |
+
"step": 381
|
| 3019 |
+
},
|
| 3020 |
+
{
|
| 3021 |
+
"epoch": 0.9899578879170716,
|
| 3022 |
+
"grad_norm": 2.046875,
|
| 3023 |
+
"learning_rate": 3.957254662385612e-09,
|
| 3024 |
+
"loss": 0.558,
|
| 3025 |
+
"step": 382
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 0.9925494007126661,
|
| 3029 |
+
"grad_norm": 2.015625,
|
| 3030 |
+
"learning_rate": 1.7588442998817124e-09,
|
| 3031 |
+
"loss": 0.5265,
|
| 3032 |
+
"step": 383
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 0.9951409135082604,
|
| 3036 |
+
"grad_norm": 2.046875,
|
| 3037 |
+
"learning_rate": 4.3972074268650023e-10,
|
| 3038 |
+
"loss": 0.5434,
|
| 3039 |
+
"step": 384
|
| 3040 |
+
},
|
| 3041 |
+
{
|
| 3042 |
+
"epoch": 0.9977324263038548,
|
| 3043 |
+
"grad_norm": 2.25,
|
| 3044 |
+
"learning_rate": 0.0,
|
| 3045 |
+
"loss": 0.5182,
|
| 3046 |
+
"step": 385
|
| 3047 |
+
}
|
| 3048 |
+
],
|
| 3049 |
+
"logging_steps": 1,
|
| 3050 |
+
"max_steps": 385,
|
| 3051 |
+
"num_input_tokens_seen": 0,
|
| 3052 |
+
"num_train_epochs": 1,
|
| 3053 |
+
"save_steps": 100,
|
| 3054 |
+
"stateful_callbacks": {
|
| 3055 |
+
"TrainerControl": {
|
| 3056 |
+
"args": {
|
| 3057 |
+
"should_epoch_stop": false,
|
| 3058 |
+
"should_evaluate": false,
|
| 3059 |
+
"should_log": false,
|
| 3060 |
+
"should_save": true,
|
| 3061 |
+
"should_training_stop": true
|
| 3062 |
+
},
|
| 3063 |
+
"attributes": {}
|
| 3064 |
+
}
|
| 3065 |
+
},
|
| 3066 |
+
"total_flos": 1.071291410939904e+17,
|
| 3067 |
+
"train_batch_size": 8,
|
| 3068 |
+
"trial_name": null,
|
| 3069 |
+
"trial_params": null
|
| 3070 |
+
}
|
checkpoint-385/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca15ebb16a59dc055f8ae01b1eb1038e869a6556aa3b7b802c58f2dde6a2993c
|
| 3 |
+
size 5304
|
config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322b2d3fc9de58487c02f1cd651d484d73244f9704de3d5feea36d002a38af0f
|
| 3 |
+
size 748
|
generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82bdd024a0ba026e4001e0433d3922a27b1242913db7be87e2851d17165b99c8
|
| 3 |
+
size 111
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:783f210de0e18c0cadd41c5bb8b4d1bbf18230cf2d1546ebf37450c870ceee8d
|
| 3 |
+
size 810702192
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8
|
| 3 |
+
size 473
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870f4e2baa6b683221fa52004d5d6f40ab8c9d31961617304b78c910c2c3caf2
|
| 3 |
+
size 2114042
|